llm-paper-daily 日常论文精选

欢迎来到 llm-paper-daily! 这是一个获取最新研究论文的每日更新和分类的平台。希望为爱好者提供 LLM 研究的前沿资讯，让您更轻松地了解该领域的最新发展。

分类

Reasoning

Date	Paper	Links & Summary
05-16	Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models _{Institution: BITS Pilani, MDSR Labs, Adobe, IIT Guhawati, National University of Singapore}
04-30	Iterative Reasoning Preference Optimization _{Institution: FAIR at Meta, New York University}
04-22	Information Re-Organization Improves Reasoning in Large Language Models _{Institution: Zhejiang University}
04-19	Relevant or Random: Can LLMs Truly Perform Analogical Reasoning? _{Institution: Nanyang Technological University, Princeton University, Salesforce Research}
04-18	Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
04-18	EVIT: Event-Oriented Instruction Tuning for Event Reasoning _{Institution: Key Laboratory of High Confidence Software Technologies (PKU), MOE, China, School of Computer Science, Peking University, Advanced Institute of Big Data}
04-17	Many-Shot In-Context Learning _{Institution: Google DeepMind}
04-16	CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity _{Institution: Intel Labs}
04-16	Self-playing Adversarial Language Game Enhances LLM Reasoning _{Institution: Tencent AI Lab}
04-11	Decomposing Label Space, Format and Discrimination: Rethinking How LLMs Respond and Solve Tasks via In-Context Learning _{Institution: Nanyang Technological University}
04-09	THOUGHTSCULPT: Reasoning with Intermediate Revision and Search _{Institution: UC Berkeley}
04-08	Evaluating Interventional Reasoning Capabilities of Large Language Models _{Institution: Université de Montréal, Google DeepMind, ServiceNow Research}
04-07	Prompting Large Language Models for Zero-shot Essay Scoring via Multi-trait Specialization _{Institution: Peking University}
03-22	Can large language models explore in-context? _{Institution: Microsoft Research, Carnegie Mellon University}
03-20	Chain-of-Interaction: Enhancing Large Language Models for Psychiatric Behavior Understanding by Dyadic Contexts _{Institution: University of Memphis, San Francisco Veterans Affairs Health Care System, University of California San Francisco}
03-13	Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments _{Institution: Nanjing University, Microsoft}
03-11	ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis _{Institution: Zhejiang University, Southeast University}
02-26	Do Large Language Models Latently Perform Multi-Hop Reasoning? _{Institution: Google DeepMind, UCL, Google Research}
02-15	Chain-of-Thought Reasoning Without Prompting _{Institution: Google DeepMind}
02-15	How to Train Data-Efficient LLMs _{Institution: Google DeepMind, University of California San Diego, Texas A&M University}
02-15	A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts _{Institution: Google DeepMind, Google Research}
02-09	InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning _{Institution: Shanghai AI Laboratory, Tsinghua University, Fudan University School of Computer Science}
02-02	MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models _{Institution: UNC Chapel Hill.}
01-25	ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases _{Institution: HKUST}
01-23	KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning _{Institution: Samsung R&D Institute India - Bangalore}
01-22	Improving Small Language Models' Mathematical Reasoning via Mix Thoughts Distillation _{Institution: Institute of Information Engineering, Chinese Academy of Sciences}
01-20	BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models _{Institution: University of Illinois Urbana-Champaign, University of Washington, Western Washington University}
01-18	Self-Rewarding Language Models _{Institution: Meta, NYU}
01-18	Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation _{Institution: The University of Tokyo, RIKEN}
01-16	MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline _{Institution: Alibaba Group}
01-11	The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models _{Institution: Johns Hopkins University}
01-11	Evidence to Generate (E2G): A Single-agent Two-step Prompting for Context Grounded and Retrieval Augmented Reasoning _{Institution: Qatar Computing Research Institute}
01-11	Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion _{Institution: Tsinghua Shenzhen International Graduate School Tsinghua University, School of Computer Science Peking University, Baidu Inc.}
01-09	Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs _{Institution: Zhejiang University, Ant Group}
01-09	Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding _{Institution: University of California San Diego, Google Cloud AI Research, Google Research}
01-09	The Critique of Critique _{Institution: The Hong Kong Polytechnic University, Shanghai Jiao Tong University, Shanghai Artificial Intelligence Laboratory}
01-08	TTMs: Fast Multi-level Tiny Time Mixers for Improved Zero-shot and Few-shot Forecasting of Multivariate Time Series _{Institution: IBM Research}
01-07	Grimoire is All You Need for Enhancing Large Language Models _{Institution: Beihang University, Renmin University of China}
01-07	Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon _{Institution: Beijing Academy of Artificial Intelligence, Renmin University of China, Nankai University}
01-06	Quartet Logic: A Four-Step Reasoning (QLFR) framework for advancing Short Text Classification _{Institution: Aerospace Information Research Institute Chinese Academy of Sciences, Key Laboratory of Target Cognition and Application Technology, University of Chinese Academy of Sciences}
01-04	On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS) _{Institution: University of South Carolina, New Mexico State University, IBM Research}
01-04	On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS) _{Institution: University of South Carolina, New Mexico State University, IBM Research}
01-04	Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives _{Institution: Zhejiang University, OPPO Research Institute}
01-04	ICE-GRT: Instruction Context Enhancement by Generative Reinforcement based Transformers _{Institution: Bytedance Inc.}
01-01	From Prompt Engineering to Prompt Science With Human in the Loop _{Institution: University of Washington}
01-01	A & B == B & A: Triggering Logical Reasoning Failures in Large Language Models _{Institution: The Chinese University of Hong Kong, Tencent AI Lab}
12-28	Challenge LLMs to Reason About Reasoning: A Benchmark to Unveil Cognitive Depth in LLMs _{Institution: Chinese University of Hong Kong, Tencent AI Lab}
12-28	Grounding-Prompter: Prompting LLM with Multimodal Information for Temporal Sentence Grounding in Long Videos _{Institution: Tsinghua University}
12-28	Improving In-context Learning via Bidirectional Alignment _{Institution: Nanyang Technological University, Princeton University, Salesforce Research USA}
12-28	Challenge LLMs to Reason About Reasoning: A Benchmark to Unveil Cognitive Depth in LLMs _{Institution: Chinese University of Hong Kong, Tencent AI Lab}
12-27	Rethinking Tabular Data Understanding with Large Language Models _{Institution: UC San Diego, USC, UC Davis}
12-27	How Robust are LLMs to In-Context Majority Label Bias? _{Institution: Amazon}
12-26	Scaling Down, LiTting Up: Efficient Zero-Shot Listwise Reranking with Seq2seq Encoder-Decoder Models _{Institution: University of Waterloo}
12-26	KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph _{Institution: Northeastern University, Neusoft AI Magic Technology Research, Neusoft Institute of Intelligent Medical Research}
12-26	Supervised Knowledge Makes Large Language Models Better In-context Learners _{Institution: School of Engineering Westlake University, Westlake Institute for Advanced Study, Peking University}
12-22	NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes _{Institution: University of Michigan, Rutgers University}
12-21	The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction _{Institution: MIT, Microsoft Research NYC}
12-21	On Task Performance and Model Calibration with Supervised and Self-Ensembled In-Context Learning _{Institution: Language Technology Lab University of Cambridge}
12-19	Active Preference Inference using Language Models and Probabilistic Reasoning _{Institution: Cornell University, Cornell Tech}
12-18	Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows _{Institution: University of Washington, Stanford University, Allen Institute for AI}
12-17	Mixed Distillation Helps Smaller Language Model Better Reasoning _{Institution: Zhejiang University, Dalian Medical University}
12-15	ProCoT: Stimulating Critical Thinking and Writing of Students through Engagement with Large Language Models (LLMs) _{Institution: Luleå University of Technology Sweden}
12-14	TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning _{Institution: National University of Singapore, University of Illinois Urbana-Champaign, Microsoft}
12-14	Boosting LLM Reasoning: Push the Limits of Few-shot Learning with Reinforced In-Context Pruning _{Institution: Hong Kong University of Science and Technology, Microsoft Research}
12-13	Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models _{Institution: University of Southern California, Amazon.com Inc.}
12-12	Comparable Demonstrations are Important in In-Context Learning: A Novel Perspective on Demonstration Selection _{Institution: Shanghai Jiao Tong University}
12-11	On Meta-Prompting _{Institution: Microsoft}
12-11	"What's important here?": Opportunities and Challenges of Using LLMs in Retrieving Information from Web Interfaces _{Institution: Carnegie Mellon University}
12-11	MMICT: Boosting Multi-Modal Fine-Tuning with In-Context Examples _{Institution: Xiamen University, Tencent YouTu Lab}
12-07	A Study on the Calibration of In-context Learning _{Institution: Harvard University}
12-07	Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration _{Institution: Renmin University of China, Beijing Institute of Technology, HKUST (GZ)}
12-05	Prompt Optimization via Adversarial In-Context Learning _{Institution: National University of Singapore, Hong Kong University of Science and Technology, Institute for Infocomm Research (I2R) A*STAR}
12-05	Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation _{Institution: Sea AI Lab, Sun Yat-sen University, Harvard University}
12-04	On the Effectiveness of Large Language Models in Domain-Specific Code Generation _{Institution: Shanghai Jiao Tong University, Chongqing University, East China Normal University}
12-04	The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning _{Institution: Allen Institute for Artificial Intelligence, University of Washington}
12-04	Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models _{Institution: Xiamen University, MBZUAI, Tencent AI Lab}
12-04	Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication _{Institution: Fudan University, National University of Singapore, Shanghai AI Laboratory}
12-02	Exploring and Improving the Spatial Reasoning Abilities of Large Language Models _{Institution: Stanford University}
12-01	On Exploring the Reasoning Capability of Large Language Models with Knowledge Graphs _{Institution: Singapore Management University, National Sun Yat-sen University}
11-30	Applying Large Language Models and Chain-of-Thought for Automatic Scoring _{Institution: University of Georgia}
11-30	IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions _{Institution: Huawei Poisson Lab}
11-29	Zero-shot Conversational Summarization Evaluations with small Large Language Models _{Institution: Intel labs}
11-29	Understanding and Improving In-Context Learning on Vision-language Models _{Institution: LMU Munich, University of Oxford}
11-23	Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions _{Institution: Tsinghua University}
11-22	Enhancing Summarization Performance through Transformer-Based Prompt Engineering in Automated Medical Reporting _{Institution: Utrecht University}
11-22	Visual In-Context Prompting _{Institution: HKUST, Microsoft Research}
11-20	Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents _{Institution: Shanghai Jiao Tong University}
11-19	TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems _{Institution: SenseTime Researc}
11-18	Orca 2: Teaching Small Language Models How to Reason _{Institution: Microsoft Research}
11-17	Exploring the Relationship between In-Context Learning and Instruction Tuning _{Institution: HKUST}
11-16	Crafting In-context Examples according to LMs' Parametric Knowledge _{Institution: The University of Texas at Austin}
11-16	Automatic Engineering of Long Prompts _{Institution: Google}
11-15	Contrastive Chain-of-Thought Prompting _{Institution: DAMO Academy, Alibaba Group}
11-15	Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models _{Institution: Tecent AI Lab}
11-13	In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax _{Institution: NYU, Microsoft}
11-11	In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering _{Institution: Stanford University}
10-31	Learning to Reason and Memorize with Self-Notes _{Institution: Meta AI}
09-19	AutoMix: Automatically Mixing Language Models _{Institution: Carnegie Mellon University}
09-12	Re-Reading Improves Reasoning in Language Models _{Institution: Institute of Information Engineering, CAS}
07-11	Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps _{Institution: UNIVERSITY OF MARYLAND}
05-26	Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models _{Institution: Singapore Management University}
05-26	Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Large Language Models _{Institution: Shanghai Jiao Tong University}
05-26	MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting _{Institution: Kyoto University}
05-23	Improving Factuality and Reasoning in Language Models through Multiagent Debate _{Institution: MIT}
05-23	ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models _{Institution: Gaoling School of Artificial Intelligence, Renmin University of China}
05-22	LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities _{Institution: Zhejiang University}
05-19	How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings _{Institution: The Ohio State University}
05-19	RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought. _{Institution: Nanjing University}
05-17	Tree of Thoughts: Deliberate Problem Solving with Large Language Models _{Institution: Princeton University}
05-10	ReAct: Synergizing Reasoning and Acting in Language Models _{Institution: Princeton University}
05-05	Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework _{Institution: Nanyang Technological University}

Agent

Date	Paper	Links & Summary
05-23	AGILE: A Novel Framework of LLM Agents _{Institution: ByteDance Research, University of Science and Technology of China, Shanghai Jiao Tong University}
05-23	Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration _{Institution: Tsinghua University, Northwestern Polytechnical University, Shanghai AI Laboratory}
05-20	Octo: An Open-Source Generalist Robot Policy _{Institution: UC Berkeley, Stanford}
05-07	Deception in Reinforced Autonomous Agents: The Unconventional Rabbit Hat Trick in Legislation _{Institution: Center for Responsible AI, IIT Madras, Princeton University}
05-06	MARE: Multi-Agents Collaboration Framework for Requirements Engineering _{Institution: Peking University}
04-18	mABC: multi-Agent Blockchain-Inspired Collaboration for root cause analysis in micro-services architecture _{Institution: Beihang University, Beijing Information Science and Technology University}
04-17	AgentKit: Flow Engineering with Graphs, not Coding _{Institution: Carnegie Mellon University, NVIDIA, Microsoft}
04-02	CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models _{Institution: East China Jiaotong University, Guangdong University of Technology, University of Toronto}
03-25	AIOS: LLM Agent Operating System _{Institution: Rutgers University}
03-15	VideoAgent: Long-form Video Understanding with Large Language Model as Agent _{Institution: Stanford University}
03-08	Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering _{Institution: Gaoling School of Artificial Intelligence Renmin University of China, Nankai University, Beijing Academy of Artificial Intelligence}
02-27	Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization _{Institution: Zhejiang University, Institute of Software Chinese Academy of Sciences, Nanjing University of Posts and Telecommunications}
02-26	LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments
02-22	OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
02-02	Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions _{Institution: Megagon Labs, Carnegie Mellon University}
02-02	AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback _{Institution: Tsinghua University, Ant Group}
01-30	Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate _{Institution: Shanghai Jiao Tong University, Carnegie Mellon University, Shanghai Artificial Intelligence Laboratory}
01-29	Beyond Direct Diagnosis: LLM-based Multi-Specialist Agent Consultation for Automatic Diagnosis _{Institution: Harbin Institute of Technology}
01-23	AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents _{Institution: Google DeepMind}
01-22	PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety _{Institution: Shanghai Artificial Intelligence Laboratory, Dalian University of Technology}
01-19	Tool-LMM: A Large Multi-Modal Model for Tool Agent Learning _{Institution: ShanghaiTech University, Meituan, UniDT}
01-14	Small LLMs Are Weak Tool Learners: A Multi-LLM Agent _{Institution: Sun Yat-sen University, Alibaba Group}
01-11	EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction _{Institution: Fudan University, Microsoft Research Asia, Zhejiang University}
01-10	AUTOACT: Automatic Agent Learning from Scratch via Self-Planning _{Institution: Zhejiang University, Alibaba Group}
01-10	Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk _{Institution: AWS AI Labs}
01-09	Agent Alignment in Evolving Social Norms _{Institution: Fudan University}
01-08	SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems _{Institution: Fudan University}
01-07	Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects _{Institution: The Chinese University of Hong Kong, DeepWisdom, Peking University}
01-06	CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models _{Institution: Harbin Institute of Technology, Kuaishou Technology}
01-05	From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models _{Institution: Beike Inc.}
12-28	GitAgent: Facilitating Autonomous Agent with GitHub by Tool Extension _{Institution: Tsinghua University, Renmin University of China}
12-28	Experiential Co-Learning of Software-Developing Agents _{Institution: Tsinghua University,Dalian University of Technology,Beijing University of Posts and Telecommunications}
12-22	Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning _{Institution: Huawei Noah's Ark Lab, University College London, University of Oxford}
12-21	De novo Drug Design using Reinforcement Learning with Multiple GPT Agents _{Institution: Tsinghua University, Microsoft Research AI}
12-21	AppAgent: Multimodal Agents as Smartphone Users _{Institution: Tencent}
12-20	AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation _{Institution: The University of Hong Kong, Shanghai Jiao Tong University, King’s College London}
12-20	AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation _{Institution: The University of Hong Kong, Shanghai Jiao Tong University}
12-18	Agent-based Learning of Materials Datasets from Scientific Literature _{Institution: University of Toronto}
12-18	Social Learning: Towards Collaborative Learning with Large Language Models _{Institution: Google, EPFL}
12-15	ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent _{Institution: Google}
12-14	Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent _{Institution: Shanghai Jiao Tong University}
12-08	PaperQA: Retrieval-Augmented Generative Agent for Scientific Research _{Institution: RAND Corporation, Carnegie Mellon University, LangChain}
12-07	An LLM Compiler for Parallel Function Calling _{Institution: UC Berkeley, ICSI, LBNL}
12-06	Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia _{Institution: Google DeepMind, Google Research}
12-05	Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction _{Institution: Zhejiang Lab, Ant Group}
11-30	Autonomous Agents in Software Development: A Vision Paper _{Institution: Tampere University}
11-29	TaskWeaver: A Code-First Agent Framework _{Institution: Microsoft}
11-29	Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering _{Institution: Sun Yat-Sen University}
11-28	AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond
11-27	RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks _{Institution: Chinese Academy of Sciences, Peking University}
11-23	Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach _{Institution: Chinese Academy of Sciences}
11-18	An Embodied Generalist Agent in 3D World _{Institution: Beijing Institute for General Artificial Intelligence}
11-16	Predictive Minds: LLMs As Atypical Active Inference Agents _{Institution: Charles University}
11-14	KTRL+F: Knowledge-Augmented In-Document Search _{Institution: KAIST AI, Samsung Research}
11-06	MetaGPT: Meta Programming for Multi-Agent Collaborative Framework _{Institution: DeepWisdom, King Abdullah University of Science and Technology}
10-16	OpenAgents: An Open Platform for Language Agents in the Wild _{Institution: The University of Hong Kong, XLang Lab}
10-16	Theory of Mind for Multi-Agent Collaboration via Large Language Models _{Institution: University of Pittsburgh}
09-29	AutoAgents: A Framework for Automatic Agent Generation _{Institution: Peking University}
09-29	ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving _{Institution: Tsinghua University, Microsoft}
09-14	Agents: An Open-source Framework for Autonomous Language Agents _{Institution: AIWaves Inc.}
08-21	AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors _{Institution: Tsinghua University}
08-21	GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems _{Institution: University of Waterloo}
08-16	AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation _{Institution: Microsoft Research}
07-25	WebArena: A Realistic Web Environment for Building Autonomous Agents _{Institution: Carnegie Mellon University}
07-24	A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis _{Institution: Google DeepMind}
07-16	Communicative Agents for Software Development _{Institution: Tsinghua University}
07-14	Language models show human-like content effects on reasoning tasks _{Institution: Google DeepMind}
07-10	RoCo: Dialectic Multi-Robot Collaboration with Large Language Models _{Institution: Columbia University}
06-13	Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control _{Institution: Nanyang Technological University}
05-23	Improving Factuality and Reasoning in Language Models through Multiagent Debate _{Institution: MIT}
05-21	Augmenting Autotelic Agents with Large Language Models _{Institution: MIT}
03-31	CAMEL: Communicative Agents for Mind Exploration of Large Language Model Society _{Institution: King Abdullah University of Science and Technology}

Knowledge and Retrieval

Date	Paper	Links & Summary
05-20	Multiple-Choice Questions are Efficient and Robust LLM Evaluators _{Institution: Shanghai Jiao Tong University}
05-20	xFinder: Robust and Pinpoint Answer Extraction for Large Language Models _{Institution: Institute for Advanced Algorithms Research, Shanghai,Renmin University of China}
05-16	SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation _{Institution: Amazon, The University of Texas at Austin}
05-16	SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation _{Institution: Amazon, The University of Texas at Austin}
05-10	UniDM: A Unified Framework for Data Manipulation with Large Language Models _{Institution: Alibaba Group, University of Science and Technology of China}
05-10	Automatic Generation of Model and Data Cards: A Step Towards Responsible AI _{Institution: CMU, MPI, ETH Zürich}
05-09	Can large language models understand uncommon meanings of common words? _{Institution: Tsinghua University, Chinese Academy of Science}
05-08	"They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations _{Institution: University of Washington, MBZUAI}
05-06	Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning _{Institution: East China Normal University}
05-02	Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models _{Institution: KAIST AI, LG AI Research, Carnegie Mellon University}
04-30	Multi-hop Question Answering over Knowledge Graphs using Large Language Models _{Institution: Microsoft}
04-29	Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models _{Institution: Cohere}
04-26	A Comprehensive Evaluation on Event Reasoning of Large Language Models _{Institution: Peking University, Advanced Institute of Big Data, Beihang University}
04-24	From Local to Global: A Graph RAG Approach to Query-Focused Summarization _{Institution: Microsoft Research, Microsoft Strategic Missions and Technologies, Microsoft Office of the CTO}
04-23	CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies _{Institution: Stanford University, IBM Research}
04-22	Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph _{Institution: University of California San Diego, Carnegie Mellon University, University of Pennsylvania}
04-22	SnapKV: LLM Knows What You are Looking for Before Generation _{Institution: University of Illinois Urbana-Champaign, Cohere, Princeton University}
04-22	LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation _{Institution: Meituan}
04-22	Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering _{Institution: Tencent Inc., Harbin Institute of Technology}
04-18	RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation _{Institution: Peking University, ByteDance Inc.}
04-16	How faithful are RAG models? Quantifying the tug-of-war between RAG and LLMs' internal prior _{Institution: Stanford University}
04-15	Compression Represents Intelligence Linearly _{Institution: The Hong Kong University of Science and Technology, Tencent}
04-11	Rho-1: Not All Tokens Are What You Need _{Institution: Xiamen University, Tsinghua University, Microsoft}
04-11	OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments _{Institution: The University of Hong Kong, CMU, Salesforce Research}
04-10	Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation _{Institution: Apple, Cupertino, CA, USA}
04-09	RULER: What's the Real Context Size of Your Long-Context Language Models? _{Institution: NVIDIA}
04-09	Event-enhanced Retrieval in Real-time Search _{Institution: Tencent Search, Platform and Content Group}
04-08	LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding _{Institution: Meta}
04-02	Long-context LLMs Struggle with Long In-context Learning _{Institution: University of Waterloo, Carnegie Mellon University}
04-02	Long-context LLMs Struggle with Long In-context Learning _{Institution: University of Waterloo, Carnegie Mellon University}
04-01	Mapping the Increasing Use of LLMs in Scientific Papers _{Institution: Stanford University, UC Santa Barbara}
04-01	LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation _{Institution: Microsoft Research Asia}
03-27	BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models _{Institution: DCST Tsinghua University, Beijing Institute of Technology, Huawei Cloud BU}
03-26	The Unreasonable Ineffectiveness of the Deeper Layers _{Institution: Meta FAIR, UMD}
03-26	COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning _{Institution: Shenzhen Institute of Advanced Technology, CAS; M-A-P; Institute of Automation, CAS}
03-18	Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression _{Institution: University of Texas at Austin, Drexel University, MIT}
03-15	RAFT: Adapting Language Model to Domain Specific RAG _{Institution: UC Berkeley}
03-15	Uni-SMART: Universal Science Multimodal Analysis and Research Transformer _{Institution: DP Technology, AI for Science Institute Beijing}
03-11	RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback _{Institution: Zhejiang University, Southeast University, Massachusetts Institute of Technology}
03-07	Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference _{Institution: UC Berkeley, Stanford, UCSD}
03-05	MathScale: Scaling Instruction Tuning for Mathematical Reasoning _{Institution: The Chinese University of Hong Kong Shenzhen, China; Microsoft Research Asia, Beijing, China; Shenzhen Research Institute of Big Data, Shenzhen, China}
02-27	REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering _{Institution: Gaoling School of Artificial Intelligence Renmin University of China, School of Information Renmin University of China}
02-25	ChatMusician: Understanding and Generating Music Intrinsically with LLM _{Institution: Hong Kong University of Science and Technology}
02-22	CriticBench: Benchmarking LLMs for Critique-Correct Reasoning _{Institution: Tsinghua University, University of Hong Kong}
02-20	TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization _{Institution: AWS AI Labs, The University of Texas at Austin, KAIST}
02-14	Premise Order Matters in Reasoning with Large Language Models _{Institution: Google DeepMind}
02-01	Can Large Language Models Understand Context? _{Institution: Georgetown University, Apple}
02-01	HR-MultiWOZ: A Task Oriented Dialogue (TOD) Dataset for HR LLM Agent _{Institution: Amazon, University of Milano-Bicocca}
01-31	LongAlign: A Recipe for Long Context Alignment of Large Language Models _{Institution: Tsinghua University, Zhipu.AI}
01-30	Incoherent Probability Judgments in Large Language Models _{Institution: Princeton University}
01-27	MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries _{Institution: Hong Kong University of Science and Technology}
01-24	Can AI Assistants Know What They Don't Know? _{Institution: Fudan University, Shanghai Artificial Intelligence Laboratory}
01-24	Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction _{Institution: Nanjing University of Science and Technology, Northeastern University, Singapore Institute of Technology}
01-24	Clue-Guided Path Exploration: An Efficient Knowledge Base Question-Answering Framework with Low Computational Resource Consumption _{Institution: Tsinghua University, Zhongguancun Laboratory, XinJiang University}
01-24	AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents _{Institution: The University of Hong Kong, Zhejiang University, Shanghai Jiao Tong University}
01-22	CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation _{Institution: Stanford University, Stability AI}
01-21	Interactive AI with Retrieval-Augmented Generation for Next Generation Networking _{Institution: Nanyang Technological University, Guangdong University of Technology, Institute for Infocomm Research, Agency for Science Technology and Research}
01-17	LLMs for Relational Reasoning: How Far are We? _{Institution: Continental-NTU Corporate Lab, Nanyang Technological University, Singapore}
01-16	RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture _{Institution: Microsoft}
01-16	Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models _{Institution: Tencent AI Lab}
01-15	A Study on Large Language Models' Limitations in Multiple-Choice Question Answering _{Institution: David R. Cheriton School of Computer Science}
01-12	Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-Translation _{Institution: Tianyu Zheng, Shuyue Guo, Xingwei Qu, Jiawei Guo, Weixu Zhang, Xinrun Du, Chenghua Lin, Wenhao Huang, Wenhu Chen, Jie Fu, Ge Zhang}
01-12	How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs _{Institution: Virginia Tech, Renmin University of China, UC Davis}
01-11	TOFU: A Task of Fictitious Unlearning for LLMs _{Institution: Carnegie Mellon University}
01-11	LLM-as-a-Coauthor: The Challenges of Detecting LLM-Human Mixcase _{Institution: LAIR Lab Lehigh University, Huazhong University of Science and Technology}
01-10	Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing _{Institution: Google Research}
01-10	CASA: Causality-driven Argument Sufficiency Assessment _{Institution: Peking University}
01-10	InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
01-09	Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search _{Institution: Nanyang Technological University Singapore}
01-04	SPEER: Sentence-Level Planning of Long Clinical Summaries via Embedded Entity Retrieval _{Institution: Columbia University}
01-02	LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
01-01	The Earth is Flat? Unveiling Factual Errors in Large Language Models _{Institution: The Chinese University of Hong Kong, Tencent AI Lab}
12-31	Improving Text Embeddings with Large Language Models _{Institution: Microsoft Corporation}
12-31	BatchEval: Towards Human-like Text Evaluation _{Institution: Beijing Institute of Technology, Xiaohongshu Inc}
12-29	Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception _{Institution: Institution: Shanghai Key Laboratory of Data Science School of Computer Science Fudan University, School of Data Science Fudan University, DataGrand Co. LTD}
12-28	Structured Packing in LLM Training Improves Long Context Utilization _{Institution: University of Warsaw, Google DeepMind, Polish Academy of Sciences}
12-26	Think and Retrieval: A Hypothesis Knowledge Graph Enhanced Medical Large Language Models _{Institution: Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science Peking University, Beijing China}
12-25	ESGReveal: An LLM-based approach for extracting structured data from ESG reports _{Institution: Alibaba Cloud, Tsinghua University, Sun Yat-Sen University}
12-22	VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation _{Institution: University of Waterloo, IN.AI Research}
12-19	A Revisit of Fake News Dataset with Augmented Fact-checking by ChatGPT
12-19	Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in ultra low-data regimes _{Institution: University of Cambridge}
12-18	G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model _{Institution: Huawei Noah's Ark Lab, The University of Hong Kong, The Hong Kong University of Science and Technology}
12-18	NoMIRACL: Knowing When You Don't Know for Robust Multilingual Retrieval-Augmented Generation _{Institution: University of Waterloo, Huawei Noah’s Ark Lab, FEEC-Unicamp Brazil}
12-18	"Paraphrasing The Original Text" Makes High Accuracy Long-Context QA _{Institution: Tsinghua University}
12-17	Distinguishing Translations by Human, NMT, and ChatGPT: A Linguistic and Statistical Approach _{Institution: Shanghai Jiao Tong University}
12-16	RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation _{Institution: CAS Key Lab of Network Data Science and Technology ICT CAS, University of Chinese Academy of Sciences Beijing China}
12-16	ProTIP: Progressive Tool Retrieval Improves Planning _{Institution: Apple}
12-16	CoAScore: Chain-of-Aspects Prompting for NLG Evaluation _{Institution: GSAI Renmin University of China}
12-16	RecPrompt: A Prompt Tuning Framework for News Recommendation Using Large Language Models _{Institution: Science Foundation Ireland (SFI), JSPS KAKENHI}
12-15	No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models _{Institution: Fudan University}
12-15	Generative Context-aware Fine-tuning of Self-supervised Speech Models _{Institution: ASAPP, Carnegie Mellon University, Toyota Technological Institute at Chicago}
12-15	Faithful Persona-based Conversational Dataset Generation with Large Language Models _{Institution: University of Southern California, Google, Information Sciences Institute}
12-15	Challenges with unsupervised LLM knowledge discovery _{Institution: Google DeepMind, Google Research}
12-15	KGLens: A Parameterized Knowledge Graph Solution to Assess What an LLM Does and Doesn't Know _{Institution: Apple}
12-14	Math-Shepherd: A Label-Free Step-by-Step Verifier for LLMs in Mathematical Reasoning _{Institution: Peking University, DeepSeek-AI, The University of Hong Kong}
12-14	Entity-Augmented Code Generation _{Institution: JetBrains}
12-14	Towards Verifiable Text Generation with Evolving Memory and Self-Reflection _{Institution: Peking University, Chinese Academy of Sciences, Baidu Inc}
12-14	TinyGSM: achieving >80% on GSM8k with small language models _{Institution: Carnegie Mellon University, Microsoft Research}
12-14	Self-Evaluation Improves Selective Generation in Large Language Models _{Institution: Google DeepMind, Google Research}
12-12	LLMEval: A Preliminary Study on How to Evaluate Large Language Models _{Institution: Fudan University, Shanghai Jiaotong University}
12-12	diff History for Long-Context Language Agents _{Institution: New York University}
12-11	Honeybee: Locality-enhanced Projector for Multimodal LLM _{Institution: Kakao Brain}
12-11	Dense X Retrieval: What Retrieval Granularity Should We Use? _{Institution: University of Washington, Tencent AI Lab}
12-10	Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs _{Institution: Microsoft Israel}
12-08	Using Program Knowledge Graph to Uncover Software Vulnerabilities
12-07	CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models _{Institution: MPI for Intelligent Systems, University of Washington}
12-05	A Hardware Evaluation Framework for Large Language Model Inference _{Institution: Princeton University}
12-04	Competition-Level Problems are Effective LLM Evaluators _{Institution: Microsoft Research Asia, Xiamen University, Microsoft Azure AI}
12-04	ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions _{Institution: Nanyang Technological University, National University of Singapore}
12-03	D-Bot: Database Diagnosis System using Large Language Models _{Institution: Tsinghua University, Pigsty, ModelBest}
12-03	TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents _{Institution: University of Southern California, Google Cloud AI}
12-03	Running cognitive evaluations on large language models: The do's and the don'ts _{Institution: Massachusetts Institute of Technology}
12-01	Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games _{Institution: Quebec AI Institute}
12-01	The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models _{Institution: University of Wisconsin - Madison}
12-01	The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models _{Institution: University of Wisconsin - Madison}
11-30	TaskBench: Benchmarking Large Language Models for Task Automation _{Institution: Zhejiang University}
11-30	What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations _{Institution: Comcast Applied AI, University of Waterloo}
11-29	Are Large Language Models Good Fact Checkers: A Preliminary Study _{Institution: Chinese Academy of Sciences}
11-29	TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models _{Institution: Harbin Institute of Technology}
11-26	UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation _{Institution: Renmin University of Chin}
11-21	Do Smaller Language Models Answer Contextualised Questions Through Memorisation Or Generalisation? _{Institution: University of Auckland}
11-21	Oasis: Data Curation and Assessment System for Pretraining of Large Language Models _{Institution: Chinese Academy of Sciences}
11-21	How Capable Can a Transformer Become? A Study on Synthetic, Interpretable Tasks _{Institution: University of Pennsylvania, MIT}
11-20	GPQA: A Graduate-Level Google-Proof Q&A Benchmark _{Institution: New York University}
11-20	Continual Learning: Applications and the Road Forward _{Institution: KU Leuven}
11-16	MacGyver: Are Large Language Models Creative Problem Solvers? _{Institution: University of California, Princeton University}
11-15	ToolTalk: Evaluating Tool-Usage in a Conversational Setting _{Institution: Microsoft Corporation}
11-14	Instruction-Following Evaluation for Large Language Models _{Institution: Google, Yale University}
11-10	Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking _{Institution: Helvia.ai}
10-17	Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection _{Institution: University of Washington}
10-11	OpsEval: A Comprehensive Task-Oriented AIOps Benchmark for Large Language Models _{Institution: Tsinghua University, Chinese Academy of Sciences}
10-10	A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection _{Institution: Peking University}
10-10	The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets _{Institution: Northeastern University, MIT}
09-26	RAGAS: Automated Evaluation of Retrieval Augmented Generation _{Institution: Cardiff University}
09-04	Benchmarking Large Language Models in Retrieval-Augmented Generation _{Institution: Chinese Information Processing Laboratory}
06-15	KoLA: Carefully Benchmarking World Knowledge of Large Language Models _{Institution: Tsinghua University}
06-07	Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering _{Institution: KAIST, MBZUAI, Amazon}
05-29	G-EVAL: NLG Evaluation using GPT-4 with Better Human Alignment _{Institution: Microsoft Cognitive Services Research}
05-24	In-Context Demonstration Selection with Cross Entropy Difference _{Institution: Microsoft Cognitive Service Research}
05-16	StructGPT: A General Framework for Large Language Model to Reason over Structured Data _{Institution: Gaoling School of Artificial Intelligence, Renmin University of China.}
02-08	A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity _{Institution: Centre for Artificial Intelligence Research}

Alignment and Hallucination

Date	Paper	Links & Summary
05-23	Agent Planning with World Knowledge Model _{Institution: Zhejiang University, Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph, National University of Singapore, Alibaba Group}
05-23	RaFe: Ranking Feedback Improves Query Rewriting for RAG _{Institution: Zhejiang University, Alibaba Group, Nanjing University}
05-23	RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models _{Institution: Amazon AWS AI, Shanghai AI Lab, Shanghai Jiaotong University}
05-14	Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Intent Resolution in LLMs _{Institution: Carnegie Mellon University, Allen Institute for AI}
05-08	ADELIE: Aligning Large Language Models on Information Extraction _{Institution: Tsinghua University}
05-01	Can a Hallucinating Model help in Reducing Human "Hallucination"? _{Institution: Stanford University, UC Berkeley}
05-01	The Real, the Better: Aligning Large Language Models with Online Human Behaviors _{Institution: Baidu Inc.}
04-30	Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom _{Institution: Shanghai Jiao Tong University}
04-26	When to Trust LLMs: Aligning Confidence with Response Quality _{Institution: Alibaba Group}
04-18	Generating Diverse Criteria On-the-Fly to Improve Point-wise LLM Rankers _{Institution: Westlake University, Alibaba Group, Zhejiang University}
04-18	Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences _{Institution: UC Berkeley}
04-17	Unifying Bias and Unfairness in Information Retrieval: A Survey of Challenges and Opportunities with Large Language Models _{Institution: Renmin University of China, Chinese Academy of Sciences, Huawei Technologies}
04-15	Learn Your Reference Model for Real Good Alignment _{Institution: Tinkoff}
04-10	Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking _{Institution: Renmin University of China, Tsinghua University}
04-08	Know When To Stop: A Study of Semantic Drift in Text Generation _{Institution: FAIR, Meta, Anthropic}
04-02	Advancing LLM Reasoning Generalists with Preference Trees
03-27	Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback
03-19	Towards Robots That Know When They Need Help: Affordance-Based Uncertainty for Large Language Model Planners _{Institution: University of Maryland}
03-13	Steering LLMs Towards Unbiased Responses: A Causality-Guided Debiasing Framework _{Institution: ByteDance Research, University of Maryland College Park, Carnegie Mellon University}
02-01	Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration _{Institution: University of Washington, University of California Berkeley, The Hong Kong University of Science and Technology}
01-25	Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning _{Institution: Columbia University, Microsoft Research, University of California Berkeley}
01-25	True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning _{Institution: Nanyang Technological University, Zhejiang University}
01-23	Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment _{Institution: Alibaba Inc.}
01-19	Mitigating Hallucinations of Large Language Models via Knowledge Consistent Alignment _{Institution: Sun Yat-sen University, Tencent AI Lab}
01-11	Patchscope: A Unifying Framework for Inspecting Hidden Representations of Language Models _{Institution: Google Research, Tel Aviv University}
01-06	The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models _{Institution: Renmin University of China, Université de Montréal}
12-26	Aligning Large Language Models with Human Preferences through Representation Engineering _{Institution: Fudan University}
12-25	Alleviating Hallucinations of Large Language Models through Induced Hallucinations _{Institution: Soochow University, Tencent AI Lab}
12-22	Reasons to Reject? Aligning Language Models with Judgments _{Institution: Tencent AI Lab, The Chinese University of Hong Kong}
12-22	Large Language Model (LLM) Bias Index -- LLMBI _{Institution: University of Oxford, University Canada West, Amazon Web Services (AWS)}
12-15	WEAK-TO-STRONG GENERALIZATION: ELICITING STRONG CAPABILITIES WITH WEAK SUPERVISION _{Institution: OpenAI}
12-11	Unlocking Anticipatory Text Generation: A Constrained Approach for Faithful Decoding with Large Language Models _{Institution: Salesforce AI Research}
12-09	Context Tuning for Retrieval Augmented Generation _{Institution: Apple}
12-02	Axiomatic Preference Modeling for Longform Question Answering
12-01	Nash Learning from Human Feedback _{Institution: Google DeepMind}
12-01	Instruction-tuning Aligns LLMs to the Human Brain _{Institution: EPFL}
11-28	Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization _{Institution: Shanghai AI Laboratory}
11-28	RELIC: Investigating Large Language Model Responses using Self-Consistency _{Institution: ETH Zurich}
11-24	Calibrated Language Models Must Hallucinate _{Institution: Microsoft Research}
11-24	Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language _{Institution: Amazon}
11-23	ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs _{Institution: Google Research}
11-18	RecExplainer: Aligning Large Language Models for Recommendation Model Interpretability _{Institution: University of Science and Technology of China}
11-14	Learning to Filter Context for Retrieval-Augmented Generation _{Institution: Carnegie Mellon University}
10-24	Correction with Backtracking Reduces Hallucination in Summarization _{Institution: Google DeepMind, Cornell University}
10-20	The History and Risks of Reinforcement Learning and Human Feedback _{Institution: Berkeley}
10-19	Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong _{Institution: Stanford University, University of Maryland}
10-19	Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks _{Institution: University of Pennsylvania, Microsoft Research}
10-05	Evaluating Hallucinations in Chinese Large Language Models _{Institution: Fudan University}
10-02	LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples _{Institution: Peking University}
10-02	Tool-Augmented Reward Modeling _{Institution: Zhejiang University, Baidu}
09-30	AutoHall: Automated Hallucination Dataset Generation for Large Language Models _{Institution: Shanghai Jiao Tong University}
09-28	Hallucination Reduction in Long Input Text Summarization _{Institution: Jadavpur University}
09-25	Aligning Large Multimodal Models with Factually Augmented RLHF _{Institution: UC Berkeley, CMU}
09-20	Chain-of-Verification Reduces Hallucination in Large Language Models _{Institution: Meta AI}
09-18	Summarization is (Almost) Dead _{Institution: Peking University}
08-22	Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models _{Institution: University of Pittsburgh, Pittsburgh, TikTok}
07-31	Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering _{Institution: Jadavpur University}
06-09	Judging LLM-as-a-judge with MT-Bench and Chatbot Arena _{Institution: UC Berkeley}
05-26	Training Socially Aligned Language Models on Simulated Social Interactions _{Institution: Google DeepMind}
05-24	Trusting Your Evidence: Hallucinate Less with Context-aware Decoding _{Institution: University of Washington}
05-22	LM vs LM: Detecting Factual Errors via Cross Examination _{Institution: Google DeepMind}
05-18	LIMA: Less Is More for Alignment _{Institution: Meta AI}
03-23	FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation _{Institution: University of Washington}
03-08	HistAlign: Improving Context Dependency in Language Generation by Aligning with History _{Institution: UNC Chapel Hill}

Application

Date	Paper	Links & Summary
05-23	PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services _{Institution: Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences}
05-21	SmartFlow: Robotic Process Automation using LLMs _{Institution: TCS Research}
05-16	MarkLLM: An Open-Source Toolkit for LLM Watermarking _{Institution: Tsinghua University, Shanghai Jiao Tong University, The University of Sydney}
05-16	Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models _{Institution: Nanyang Technological University, University of Science and Technology of China, University of Aberdeen}
05-09	LLMPot: Automated LLM-based Industrial Protocol and Physical Process Emulation for ICS Honeypots _{Institution: New York University Abu Dhabi}
05-09	Exploring the Potential of Human-LLM Synergy in Advancing Qualitative Analysis: A Case Study on Mental-Illness Stigma
05-09	An Automatic Prompt Generation System for Tabular Data Tasks
05-07	Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application _{Institution: Kuaishou Technology, Southeast University}
05-07	Toward In-Context Teaching: Adapting Examples to Students' Misconceptions _{Institution: MIT CSAIL}
05-03	What matters when building vision-language models? _{Institution: Hugging Face, Sorbonne Université}
05-02	How Can I Get It Right? Using GPT to Rephrase Incorrect Trainee Responses _{Institution: Carnegie Mellon University}
05-01	"I'm Not Sure, But...": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust _{Institution: Princeton University, Microsoft}
05-01	Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3
04-25	How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites _{Institution: Shanghai AI Laboratory, SenseTime Research, Tsinghua University}
04-19	LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency _{Institution: Nanyang Technological University, DAMO Academy Alibaba Group, Singapore University of Technology and Design}
04-17	A Deep Dive into Large Language Models for Automated Bug Localization and Repair _{Institution: University of Virginia, Purdue University, Amazon Web Services}
04-14	Emerging Platforms Meet Emerging LLMs: A Year-Long Journey of Top-Down Development
04-11	ChatGPT Can Predict the Future when it Tells Stories Set in the Future About the Past _{Institution: Baylor University}
04-11	ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback _{Institution: University of Central Florida, ByteDance Inc}
04-10	"We Need Structured Output": Towards User-centered Constraints on Large Language Model Output _{Institution: Google Research}
04-03	PromptRPA: Generating Robotic Process Automation on Smartphones from Textual Prompts _{Institution: Shanghai Jiao Tong University, CMU}
04-02	Octopus v2: On-device language model for super agent _{Institution: Stanford University}
04-02	LLM-ABR: Designing Adaptive Bitrate Algorithms via Large Language Models _{Institution: Microsoft}
03-13	Scaling Instructable Agents Across Many Simulated Worlds
03-11	Stealing Part of a Production Language Model _{Institution: Google DeepMind, ETH Zurich, University of Washington}
03-08	Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context _{Institution: Google}
03-07	Yi: Open Foundation Models by 01.AI _{Institution: 01.AI}
03-05	Design2Code: How Far Are We From Automating Front-End Engineering? _{Institution: Stanford University, Georgia Tech, Microsoft}
02-29	Beyond Language Models: Byte Models are Digital World Simulators _{Institution: Microsoft Research Asia}
02-29	StarCoder 2 and The Stack v2: The Next Generation _{Institution: ServiceNow, Hugging Face}
02-27	The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits _{Institution: Microsoft, University of Chinese Academy of Sciences}
02-27	EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions _{Institution: Alibaba Group}
02-27	Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models _{Institution: OpenAI}
02-26	Improving LLM-based Machine Translation with Systematic Self-Correction _{Institution: Zhejiang University, Tencent, Angelalign Technology Inc.}
02-23	Genie: Generative Interactive Environments _{Institution: Google DeepMind, University of British Columbia}
02-19	AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling _{Institution: Fudan University, Multimodal Art Projection Research Community, Shanghai AI Laboratory}
02-16	FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models _{Institution: The University of British Columbia & Invertible AI}
02-16	SPAR: Personalized Content-Based Recommendation via Long Engagement Attention _{Institution: The University of British Columbia, Meta}
02-02	LimSim++: A Closed-Loop Platform for Deploying Multimodal LLMs in Autonomous Driving _{Institution: Shanghai Artificial Intelligence Laboratory, College of Control Science and Engineering Zhejiang University}
01-30	Recovering Mental Representations from Large Language Models with Markov Chain Monte Carlo _{Institution: Princeton University, University of Warwick}
01-29	LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning _{Institution: Nanyang Technological University}
01-19	Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning _{Institution: MIT}
01-17	Vlogger: Make Your Dream A Vlog _{Institution: Shanghai Jiao Tong University, Shanghai AI Laboratory, Shenzhen Institute of Advanced Technology Chinese Academy of Sciences}
01-16	SpecGen: Automated Generation of Formal Program Specifications via Large Language Models _{Institution: Nanjing University, Nanyang Technological University, Singapore Management University}
01-12	TestSpark: IntelliJ IDEA's Ultimate Test Generation Companion _{Institution: JetBrains Research, Delft University of Technology}
01-12	From Automation to Augmentation: Large Language Models Elevating Essay Scoring Landscape _{Institution: Tsinghua University, University of Maryland, Beijing Xicheng Educational Research Institute}
01-12	Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation _{Institution: Nanyang Technological University, Fudan University}
01-10	Prompting Large Language Models for Recommender Systems: A Comprehensive Framework and Empirical Analysis _{Institution: Renmin University of China, Beijing Key Laboratory of Big Data Management and Analysis Methods, Meituan Group}
01-10	Leveraging Print Debugging to Improve Code Generation in Large Language Models _{Institution: Zhejiang University, ByteDance}
01-08	MARG: Multi-Agent Review Generation for Scientific Papers _{Institution: Northwestern University, The Hebrew University of Jerusalem, Allen Institute for AI}
01-05	Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache _{Institution: Alibaba Group, Shanghai Jiao Tong University}
01-04	Using LLM to select the right SQL Query from candidates _{Institution: Peking University}
01-04	LLM Augmented LLMs: Expanding Capabilities through Composition _{Institution: Google Research, Google DeepMind}
01-03	MedSumm: A Multimodal Approach to Summarizing Code-Mixed Hindi-English Clinical Queries _{Institution: Indian Institute of Technology Patna, Stanford University, Amazon GenAI}
01-03	Social Media Ready Caption Generation for Brands _{Institution: Adobe Research India}
12-29	DB-GPT: Empowering Database Interactions with Private Large Language Models _{Institution: Alibaba Group}
12-29	The Right Prompts for the Job: Repair Code-Review Defects with Large Language Model _{Institution: Ant Group, Nanjing University}
12-29	Building Efficient Universal Classifiers with Natural Language Inference _{Institution: Vrije Universiteit Amsterdam, University of London Royal Holloway, Hugging Face}
12-28	DrugAssist: A Large Language Model for Molecule Optimization _{Institution: Tencent AI Lab, Department of Computer Science Hunan University}
12-27	Conversational Question Answering with Reformulations over Knowledge Graph _{Institution: University of Illinois at Urbana-Champaign, Amazon}
12-27	Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges _{Institution: Shanghai Jiao Tong University (SJTU)}
12-26	RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation _{Institution: City University of Hong Kong, The Chinese University of Hong Kong, Hangdian University}
12-22	YAYI 2: Multilingual Open-Source Large Language Models _{Institution: Beijing Wenge Technology Co. Ltd., Institute of Automation Chinese Academy of Sciences}
12-20	Lampr: Boosting the Effectiveness of Language-Generic Program Reduction via Large Language Models _{Institution: University of Waterloo, The Hong Kong University of Science and Technology, Concordia University}
12-20	Generative Multimodal Models are In-Context Learners _{Institution: Beijing Academy of Artificial Intelligence, Tsinghua University, Peking University}
12-19	Text-Conditioned Resampler For Long Form Video Understanding _{Institution: University of Oxford, Google, Google DeepMind}
12-18	Towards Better Serialization of Tabular Data for Few-shot Classification with Large Language Models _{Institution: Carnegie Mellon University}
12-18	MAC-SQL: Multi-Agent Collaboration for Text-to-SQL _{Institution: Beihang University, Tencent Cloud AI}
12-15	GSVA: Generalized Segmentation via Multimodal Large Language Models _{Institution: Tsinghua University}
12-14	CogAgent: A Visual Language Model for GUI Agents _{Institution: Tsinghua University, Zhipu AI}
12-14	StemGen: A music generation model that listens _{Institution: SAMI, ByteDance Inc.}
12-14	Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft _{Institution: CUHK-SenseTime Joint Laboratory, Shanghai AI Laboratory, Tsinghua University}
12-13	SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention _{Institution: The Swiss AI Lab IDSIA USI & SUPSI, AI Initiative KAUST, Center for Brain Science Harvard University}
12-13	E&V: Prompting Large Language Models to Perform Static Analysis by Pseudo-code Execution and Verification _{Institution: UC Riverside, Microsoft Research}
12-13	Knowledge-Aware Artifact Image Synthesis with LLM-Enhanced Prompting and Multi-Source Supervision _{Institution: Peking University}
12-12	LLM in a flash: Efficient Large Language Model Inference with Limited Memory _{Institution: Apple}
12-11	Oracle-based Protocol Testing with Eywa _{Institution: Microsoft Research}
12-09	Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis _{Institution: Shanghai Jiao Tong University}
12-07	Generating Illustrated Instructions _{Institution: GenAI Meta, Columbia University}
12-06	Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment _{Institution: Zhejiang Lab}
12-06	OneLLM: One Framework to Align All Modalities with Language _{Institution: MMLab The Chinese University of Hong Kong, Shanghai Artificial Intelligence Laboratory}
12-05	A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education _{Institution: Carnegie Mellon University}
12-04	LLMs Accelerate Annotation for Medical Information Extraction _{Institution: Google Research}
12-02	Large Language Models Are Zero-Shot Text Classifiers _{Institution: Florida Atlantic University}
12-01	Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses _{Institution: Google}
12-01	Improve Supervised Representation Learning with Masked Image Modeling _{Institution: Google Research, OpenAI}
11-30	PoseGPT: Chatting about 3D Human Pose _{Institution: Max Planck Institute for Intelligent Systems, Meshcapade}
11-30	Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text _{Institution: The University of Tokyo}
11-30	MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation _{Institution: University of Science and Technology of China, Microsoft Research Asia}
11-29	Large Language Models for Networking: Applications, Enabling Techniques, and Challenges _{Institution: BUPT}
11-29	How to Build an AI Tutor that Can Adapt to Any Course and Provide Accurate Answers Using Large Language Model and Retrieval-Augmented Generation _{Institution: The Education University of Hong Kong}
11-28	ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up? _{Institution: Nanyang Technological University}
11-28	Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation _{Institution: Alibaba Group}
11-28	Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine _{Institution: Microsoft}
11-28	LLaFS: When Large-Language Models Meet Few-Shot Segmentation _{Institution: Singapore University of Technology and Design, Zhejiang University}
11-23	LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes _{Institution: ASRI}
11-23	FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline _{Institution: Sber AI}
11-22	XAGen: 3D Expressive Human Avatars Generation _{Institution: National University of Singapore, ByteDance}
11-21	AcademicGPT: Empowering Academic Research _{Institution: International Digital Economy Academy}
11-21	A Survey on Multimodal Large Language Models for Autonomous Driving _{Institution: Purdue University}
11-13	Can LLMs Patch Security Issues? _{Institution: School of Computer Science Atlanta}
11-05	ChaTA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs _{Institution: Cornell University, Microsoft Research}
11-01	LLMRec: Large Language Models with Graph Augmentation for Recommendation _{Institution: University of Hong Kong, Baidu}
10-10	GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models _{Institution: Microsoft Research}
08-18	Learning Representations on Logs for AIOps _{Institution: IBM Research}

Pre-training and Instruction Fine-tuning

Date	Paper	Links & Summary
05-21	G-DIG: Towards Gradient-based DIverse and hiGh-quality Instruction Data Selection for Machine Translation _{Institution: ByteDance Research}
05-20	OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework _{Institution: OpenLLMAI Team, ByteDance Inc., Netease Fuxi AI Lab}
05-19	Your Transformer is Secretly Linear _{Institution: AIRI, Skoltech, SberAI}
05-17	Prompt Exploration with Prompt Regression _{Institution: Carnegie Mellon University, Massachusetts Institute of Technology, University of Michigan}
05-15	ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models _{Institution: Microsoft Research Asia, Harvard University, Peking University}
05-15	LoRA Learns Less and Forgets Less _{Institution: Columbia University, Databricks}
05-13	RLHF Workflow: From Reward Modeling to Online RLHF _{Institution: Salesforce AI Research, University of Illinois Urbana-Champaign}
05-07	QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving _{Institution: MIT, NVIDIA}
04-30	Better & Faster Large Language Models via Multi-token Prediction _{Institution: FAIR at Meta}
04-29	LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report _{Institution: Predibase}
04-25	Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding _{Institution: Meta, University of Toronto, Carnegie Mellon University}
04-13	Intuition-aware Mixture-of-Rank-1-Experts for Parameter Efficient Finetuning _{Institution: Nanjing University, University of California}
04-12	Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length _{Institution: AI at Meta, University of Southern California, Carnegie Mellon University}
04-10	Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention _{Institution: Google}
04-08	LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding _{Institution: Alibaba Group, Zhejiang University}
04-07	Radial Networks: Dynamic Layer Routing for High-Performance Large Language Models _{Institution: Cornell University}
04-04	Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences _{Institution: Microsoft Research}
04-04	ReFT: Representation Finetuning for Language Models _{Institution: Stanford University, Pr(Ai)2R Group}
04-01	Efficiently Distilling LLMs for Edge Applications _{Institution: IBM Research}
04-01	Prompt-prompted Mixture of Experts for Efficient LLM Generation _{Institution: CMU}
03-28	Jamba: A Hybrid Transformer-Mamba Language Model _{Institution: AI21 Labs}
03-26	LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning _{Institution: The Hong Kong University of Science and Technology, University of Illinois Urbana-Champaign}
03-12	Chronos: Learning the Language of Time Series _{Institution: Amazon Web Services, UC San Diego, University of Freiburg}
03-08	Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
02-29	SEED: Customize Large Language Models with Sample-Efficient Adaptation for Code Generation _{Institution: Peking University}
02-27	When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method _{Institution: Google DeepMind}
02-20	Instruction-tuned Language Models are Better Knowledge Learners _{Institution: FAIR at Meta, Carnegie Mellon University, University of Washington}
02-01	Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing _{Institution: Nanyang Technological University, Institute for Infocomm Research A*STAR, Salesforce Research}
01-29	SelectLLM: Can LLMs Select Important Instructions to Annotate? _{Institution: University of Minnesota, Carnegie Mellon University}
01-26	EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty _{Institution: Peking University, Microsoft Research, University of Waterloo}
01-19	Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads _{Institution: Princeton University, Together AI, University of Illinois Urbana-Champaign}
01-18	A Fast, Performant, Secure Distributed Training Framework For Large Language Model _{Institution: Ant Group China}
01-18	ChatQA: Building GPT-4 Level Conversational QA Models _{Institution: NVIDIA}
01-17	ReFT: Reasoning with Reinforced Fine-Tuning _{Institution: ByteDance Research}
01-16	Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation _{Institution: Johns Hopkins University, Microsoft}
01-15	MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models _{Institution: Microsoft Research India}
01-12	APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding _{Institution: Tsinghua University, Zhipu AI}
01-12	An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models _{Institution: University of Washington Seattle, University of Wisconsin-Madison, Stanford University}
01-11	Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint _{Institution: Gaoling School of Artificial Intelligence, Renmin University of China; School of Information, Renmin University of China; Kuaishou Technology, Beijing China.}
12-26	A Prompt Learning Framework for Source Code Summarization _{Institution: Nanyang Technological University, Tencent Inc., Nanjing University}
12-22	Generative AI Beyond LLMs: System Implications of Multi-Modal Generation
12-22	Plan, Posture and Go: Towards Open-World Text-to-Motion Generation _{Institution: Tsinghua University, Microsoft Research Asia}
12-20	Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy _{Institution: Ant Group}
12-20	Mini-GPTs: Efficient Large Language Models through Contextual Pruning _{Institution: Massachusetts Institute of Technology}
12-20	Time is Encoded in the Weights of Finetuned Language Models
12-15	The Art of Balancing: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment _{Institution: NLP Group Fudan University, Hikvision Inc}
12-14	Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention _{Institution: Tencent AI Lab Seattle}
12-12	VILA: On Pre-training for Visual Language Models _{Institution: NVIDIA, MIT}
12-11	Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes _{Institution: Zhejiang University, Alibaba Group}
12-09	Sim-GPT: Text Similarity via GPT Annotated Data _{Institution: Shannon.AI, Zhejiang University, Bytedance}
12-09	Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge _{Institution: Northeastern University, Oracle}
12-06	Controllable Human-Object Interaction Synthesis _{Institution: Stanford University, FAIR Meta}
12-05	RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze! _{Institution: University of Waterloo}
11-28	Prompting in Autoregressive Large Language Models _{Institution: George Mason University}
11-28	Training Chain-of-Thought via Latent-Variable Inference _{Institution: Google}
11-28	RankingGPT: Empowering Large Language Models in Text Ranking with Progressive Enhancement _{Institution: Alibaba Group}
11-23	Diffusion Model Alignment Using Direct Preference Optimization _{Institution: Nikhil Naik, Stanford University}
11-22	LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms _{Institution: Princeton University}
11-21	Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey _{Institution: Nanjing University}
11-21	Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks _{Institution: University of Cambridge}
11-18	Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning _{Institution: Technical University of Darmstadt, University of Cambridge}
11-17	Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2 _{Institution: Allen Institute for AI}
11-15	Exponentially Faster Language Modelling _{Institution: ETH Zurich}
11-15	Memory Augmented Language Models through Mixture of Word Experts _{Institution: Google Research}
11-14	Fine-tuning Language Models for Factuality _{Institution: Stanford University}
07-12	Instruction Mining: When Data Mining Meets Large Language Model Finetuning _{Institution: Carnegie Mellon University}

Survey

Date	Paper	Links & Summary
04-25	Continual Learning of Large Language Models: A Comprehensive Survey _{Institution: Rutgers University, Wuhan University, Huazhong University of Science and Technology}
04-24	Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs _{Institution: Shanghai Jiao Tong University, UC San Diego, Duke University}
04-23	A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applications _{Institution: Hong Kong Baptist University}
04-22	A Survey on Efficient Inference for Large Language Models _{Institution: Tsinghua University}
04-22	A Survey on Self-Evolution of Large Language Models _{Institution: Peking University, Alibaba Group, Nanyang Technological University}
04-09	Privacy Preserving Prompt Engineering: A Survey _{Institution: University of Arkansas}
04-01	AIOps Solutions for Incident Management: Technical Guidelines and A Comprehensive Literature Review _{Institution: University of Lyon, INSA Lyon, Infologic}
01-24	MM-LLMs: Recent Advances in MultiModal Large Language Models _{Institution: Tencent AI Lab, Kyoto University, Mohamed Bin Zayed University of Artificial Intelligence}
01-15	The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey _{Institution: Technology Innovation Institute UAE, Islamic University of Technology Bangladesh, Stanford University, Amazon GenAI, AI Institute University of South Carolina}
01-11	Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems _{Institution: Zhongguancun Laboratory, Tsinghua University, Institute of Information Engineering Chinese Academy of Sciences}
01-09	Large Language Models for Robotics: Opportunities, Challenges, and Perspectives _{Institution: Northwestern Polytechnical University, University of Georgia, Shaanxi Normal University}
01-02	A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models _{Institution: Islamic University of Technology Bangladesh, University of South Carolina, Stanford University}
12-22	A Survey of Reinforcement Learning from Human Feedback _{Institution: LMU Munich, Duke Kunshan University}
12-18	Retrieval-Augmented Generation for Large Language Models: A Survey _{Institution: Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Fudan University}
12-18	From Google Gemini to OpenAI Q-Star: A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape _{Institution: Cyberstronomy Pty Ltd, Academies Australasia Polytechnic, Massey University}
12-16	A Survey on Robotic Manipulation of Deformable Objects: Recent Advances, Open Challenges and New Frontiers _{Institution: Tongji University, National Natural Science Foundation of China, Shanghai Municipal Science and Technology Major Project}
12-09	NLLG Quarterly arXiv Report 09/23: What are the most influential current AI Papers? _{Institution: University of Mannheim, University of Bielefeld}
12-06	Efficient Large Language Models: A Survey _{Institution: The Ohio State University, Google Research, Amazon AWS AI}
12-04	A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly _{Institution: Elsevier}
12-04	Data Management For Large Language Models: A Survey _{Institution: Peking University, Huawei Noah’s Ark Lab}
11-28	Graph Prompt Learning: A Comprehensive Survey and Beyond _{Institution: The Chinese University of Hong Kong, Hong Kong University of Science and Technology, Fudan University}
11-21	Prompting Frameworks for Large Language Models: A Survey _{Institution: Zhejiang University}
10-16	A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future _{Institution: Harbin Institute of Technology, Huawei}
09-03	Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models _{Institution: Tencent AI lab}
06-01	Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation _{Institution: Carnegie Mellon University}
03-31	A Survey of Large Language Models _{Institution: Renmin University of China}
03-15	GPT-4 Technical Report _{Institution: OpenAI}
02-15	Augmented Language Models: a Survey _{Institution: Meta AI}

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

CATEGORIES.md

CATEGORIES.md

llm-paper-daily 日常论文精选

目录

分类

Reasoning

Agent

Knowledge and Retrieval

Alignment and Hallucination

Application

Pre-training and Instruction Fine-tuning

Survey

Files

CATEGORIES.md

Latest commit

History

CATEGORIES.md

File metadata and controls

llm-paper-daily 日常论文精选

目录

分类

Reasoning

Agent

Knowledge and Retrieval

Alignment and Hallucination

Application

Pre-training and Instruction Fine-tuning

Survey