[](summary/2023-02/2305.12487.md) |
|
| **CAMEL: Communicative Agents for Mind Exploration of Large Language Model Society**
[](https://arxiv.org/pdf/2303.17760.pdf)
[](summary/2023-02/2303.1776.md) |
### Knowledge and Retrieval
| Date | Paper | Links & Summary |
| --- | --- | --- |
|
05-20 | **Multiple-Choice Questions are Efficient and Robust LLM Evaluators**
**Institution:** Shanghai Jiao Tong University
|
[](http://arxiv.org/pdf/2405.11966v2)
[](summary/2023-02/2405.11966.md) |
|
05-20 | **xFinder: Robust and Pinpoint Answer Extraction for Large Language Models**
**Institution:** Institute for Advanced Algorithms Research, Shanghai,Renmin University of China
|
[](http://arxiv.org/pdf/2405.11874v1)
[](summary/2023-02/2405.11874.md) |
|
05-16 | **SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation**
**Institution:** Amazon, The University of Texas at Austin
|
[](http://arxiv.org/pdf/2405.10040v1)
[](summary/2023-02/2405.1004.md) |
|
05-16 | **SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation**
**Institution:** Amazon, The University of Texas at Austin
|
[](http://arxiv.org/pdf/2405.10040v1)
[](summary/2023-02/2405.1004.md) |
|
05-10 | **UniDM: A Unified Framework for Data Manipulation with Large Language Models**
**Institution:** Alibaba Group, University of Science and Technology of China
|
[](http://arxiv.org/pdf/2405.06510v1)
[](summary/2023-02/2405.0651.md) |
|
05-10 | **Automatic Generation of Model and Data Cards: A Step Towards Responsible AI**
**Institution:** CMU, MPI, ETH Zürich
|
[](http://arxiv.org/pdf/2405.06258v1)
[](summary/2023-02/2405.06258.md) |
|
05-09 | **Can large language models understand uncommon meanings of common words?**
**Institution:** Tsinghua University, Chinese Academy of Science
|
[](http://arxiv.org/pdf/2405.05741v1)
[](summary/2023-02/2405.05741.md) |
|
05-08 | **"They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations**
**Institution:** University of Washington, MBZUAI
|
[](http://arxiv.org/pdf/2405.05378v1)
[](summary/2023-02/2405.05378.md) |
|
05-06 | **Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning**
**Institution:** East China Normal University
|
[](http://arxiv.org/pdf/2405.03279v1)
[](summary/2023-02/2405.03279.md) |
|
05-02 | **Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models**
**Institution:** KAIST AI, LG AI Research, Carnegie Mellon University
|
[](http://arxiv.org/pdf/2405.01535v1)
[](summary/2023-02/2405.01535.md) |
|
04-30 | **Multi-hop Question Answering over Knowledge Graphs using Large Language Models**
**Institution:** Microsoft
|
[](http://arxiv.org/pdf/2404.19234v1)
[](summary/2023-02/2404.19234.md) |
|
04-29 | **Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models**
**Institution:** Cohere
|
[](http://arxiv.org/pdf/2404.18796v2)
[](summary/2023-02/2404.18796.md) |
|
04-26 | **A Comprehensive Evaluation on Event Reasoning of Large Language Models**
**Institution:** Peking University, Advanced Institute of Big Data, Beihang University
|
[](http://arxiv.org/pdf/2404.17513v1)
[](summary/2023-02/2404.17513.md) |
|
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
|
[](http://arxiv.org/pdf/2404.16130v1)
[](summary/2023-02/2404.1613.md) |
|
04-23 | **CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies**
**Institution:** Stanford University, IBM Research
|
[](http://arxiv.org/pdf/2404.15238v1)
[](summary/2023-02/2404.15238.md) |
|
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
|
[](http://arxiv.org/pdf/2404.14372v1)
[](summary/2023-02/2404.14372.md) |
|
04-22 | **SnapKV: LLM Knows What You are Looking for Before Generation**
**Institution:** University of Illinois Urbana-Champaign, Cohere, Princeton University
|
[](http://arxiv.org/pdf/2404.14469v1)
[](summary/2023-02/2404.14469.md) |
|
04-22 | **LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation**
**Institution:** Meituan
|
[](http://arxiv.org/pdf/2404.14043v1)
[](summary/2023-02/2404.14043.md) |
|
04-22 | **Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering**
**Institution:** Tencent Inc., Harbin Institute of Technology
|
[](http://arxiv.org/pdf/2404.14464v1)
[](summary/2023-02/2404.14464.md) |
|
04-18 | **RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation**
**Institution:** Peking University, ByteDance Inc.
|
[](http://arxiv.org/pdf/2404.12457v1)
[](summary/2023-02/2404.12457.md) |
|
04-16 | **How faithful are RAG models? Quantifying the tug-of-war between RAG and LLMs' internal prior**
**Institution:** Stanford University
|
[](http://arxiv.org/pdf/2404.10198v1)
[](summary/2023-02/2404.10198.md) |
|
04-15 | **Compression Represents Intelligence Linearly**
**Institution:** The Hong Kong University of Science and Technology, Tencent
|
[](http://arxiv.org/pdf/2404.09937v1)
[](summary/2023-02/2404.09937.md) |
|
04-11 | **Rho-1: Not All Tokens Are What You Need**
**Institution:** Xiamen University, Tsinghua University, Microsoft
|
[](http://arxiv.org/pdf/2404.07965v1)
[](summary/2023-02/2404.07965.md) |
|
04-11 | **OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments**
**Institution:** The University of Hong Kong, CMU, Salesforce Research
|
[](http://arxiv.org/pdf/2404.07972v1)
[](summary/2023-02/2404.07972.md) |
|
04-10 | **Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation**
**Institution:** Apple, Cupertino, CA, USA
|
[](http://arxiv.org/pdf/2404.06910v1)
[](summary/2023-02/2404.0691.md) |
|
04-09 | **RULER: What's the Real Context Size of Your Long-Context Language Models?**
**Institution:** NVIDIA
|
[](http://arxiv.org/pdf/2404.06654v1)
[](summary/2023-02/2404.06654.md) |
|
04-09 | **Event-enhanced Retrieval in Real-time Search**
**Institution:** Tencent Search, Platform and Content Group
|
[](http://arxiv.org/pdf/2404.05989v1)
[](summary/2023-02/2404.05989.md) |
|
04-08 | **LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding**
**Institution:** Meta
|
[](http://arxiv.org/pdf/2404.05825v1)
[](summary/2023-02/2404.05825.md) |
|
04-02 | **Long-context LLMs Struggle with Long In-context Learning**
**Institution:** University of Waterloo, Carnegie Mellon University
|
[](http://arxiv.org/pdf/2404.02060v2)
[](summary/2023-02/2404.0206.md) |
|
04-02 | **Long-context LLMs Struggle with Long In-context Learning**
**Institution:** University of Waterloo, Carnegie Mellon University
|
[](http://arxiv.org/pdf/2404.02060v2)
[](summary/2023-02/2404.0206.md) |
|
04-01 | **Mapping the Increasing Use of LLMs in Scientific Papers**
**Institution:** Stanford University, UC Santa Barbara
|
[](http://arxiv.org/pdf/2404.01268v1)
[](summary/2023-02/2404.01268.md) |
|
04-01 | **LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation**
**Institution:** Microsoft Research Asia
|
[](http://arxiv.org/pdf/2404.00998v1)
[](summary/2023-02/2404.00998.md) |
|
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
|
[](http://arxiv.org/pdf/2403.18365v1)
[](summary/2023-02/2403.18365.md) |
|
03-26 | **The Unreasonable Ineffectiveness of the Deeper Layers**
**Institution:** Meta FAIR, UMD
|
[](http://arxiv.org/pdf/2403.17887v1)
[](summary/2023-02/2403.17887.md) |
|
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
|
[](http://arxiv.org/pdf/2403.18058v1)
[](summary/2023-02/2403.18058.md) |
|
03-18 | **Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression**
**Institution:** University of Texas at Austin, Drexel University, MIT
|
[](http://arxiv.org/pdf/2403.15447v1)
[](summary/2023-02/2403.15447.md) |
|
03-15 | **RAFT: Adapting Language Model to Domain Specific RAG**
**Institution:** UC Berkeley
|
[](http://arxiv.org/pdf/2403.10131v1)
[](summary/2023-02/2403.10131.md) |
|
03-15 | **Uni-SMART: Universal Science Multimodal Analysis and Research Transformer**
**Institution:** DP Technology, AI for Science Institute Beijing
|
[](http://arxiv.org/pdf/2403.10301v1)
[](summary/2023-02/2403.10301.md) |
|
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
|
[](http://arxiv.org/pdf/2403.06840v1)
[](summary/2023-02/2403.0684.md) |
|
03-07 | **Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference**
**Institution:** UC Berkeley, Stanford, UCSD
|
[](http://arxiv.org/pdf/2403.04132v1)
[](summary/2023-02/2403.04132.md) |
|
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
|
[](http://arxiv.org/pdf/2403.02884v1)
[](summary/2023-02/2403.02884.md) |
|
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
|
[](http://arxiv.org/pdf/2402.17497v1)
[](summary/2023-02/2402.17497.md) |
|
02-25 | **ChatMusician: Understanding and Generating Music Intrinsically with LLM**
**Institution:** Hong Kong University of Science and Technology
|
[](http://arxiv.org/pdf/2402.16153v1)
[](summary/2023-02/2402.16153.md) |
|
02-22 | **CriticBench: Benchmarking LLMs for Critique-Correct Reasoning**
**Institution:** Tsinghua University, University of Hong Kong
|
[](http://arxiv.org/pdf/2402.14809v1)
[](summary/2023-02/2402.14809.md) |
|
02-20 | **TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization**
**Institution:** AWS AI Labs, The University of Texas at Austin, KAIST
|
[](http://arxiv.org/pdf/2402.13249v1)
[](summary/2023-02/2402.13249.md) |
|
02-14 | **Premise Order Matters in Reasoning with Large Language Models**
**Institution:** Google DeepMind
|
[](http://arxiv.org/pdf/2402.08939v1)
[](summary/2023-02/2402.08939.md) |
|
02-01 | **Can Large Language Models Understand Context?**
**Institution:** Georgetown University, Apple
|
[](http://arxiv.org/pdf/2402.00858v1)
[](summary/2023-02/2402.00858.md) |
|
02-01 | **HR-MultiWOZ: A Task Oriented Dialogue (TOD) Dataset for HR LLM Agent**
**Institution:** Amazon, University of Milano-Bicocca
|
[](http://arxiv.org/pdf/2402.01018v1)
[](summary/2023-02/2402.01018.md) |
|
01-31 | **LongAlign: A Recipe for Long Context Alignment of Large Language Models**
**Institution:** Tsinghua University, Zhipu.AI
|
[](http://arxiv.org/pdf/2401.18058v1)
[](summary/2023-02/2401.18058.md) |
|
01-30 | **Incoherent Probability Judgments in Large Language Models**
**Institution:** Princeton University
|
[](http://arxiv.org/pdf/2401.16646v1)
[](summary/2023-02/2401.16646.md) |
|
01-27 | **MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries**
**Institution:** Hong Kong University of Science and Technology
|
[](http://arxiv.org/pdf/2401.15391v1)
[](summary/2023-02/2401.15391.md) |
|
01-24 | **Can AI Assistants Know What They Don't Know?**
**Institution:** Fudan University, Shanghai Artificial Intelligence Laboratory
|
[](http://arxiv.org/pdf/2401.13275v1)
[](summary/2023-02/2401.13275.md) |
|
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
|
[](http://arxiv.org/pdf/2401.13598v1)
[](summary/2023-02/2401.13598.md) |
|
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
|
[](http://arxiv.org/pdf/2401.13444v1)
[](summary/2023-02/2401.13444.md) |
|
01-24 | **AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents**
**Institution:** The University of Hong Kong, Zhejiang University, Shanghai Jiao Tong University
|
[](http://arxiv.org/pdf/2401.13178v1)
[](summary/2023-02/2401.13178.md) |
|
01-22 | **CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation**
**Institution:** Stanford University, Stability AI
|
[](http://arxiv.org/pdf/2401.12208v1)
[](summary/2023-02/2401.12208.md) |
|
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
|
[](http://arxiv.org/pdf/2401.11391v1)
[](summary/2023-02/2401.11391.md) |
|
01-17 | **LLMs for Relational Reasoning: How Far are We?**
**Institution:** Continental-NTU Corporate Lab, Nanyang Technological University, Singapore
|
[](http://arxiv.org/pdf/2401.09042v1)
[](summary/2023-02/2401.09042.md) |
|
01-16 | **RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture**
**Institution:** Microsoft
|
[](http://arxiv.org/pdf/2401.08406v1)
[](summary/2023-02/2401.08406.md) |
|
01-16 | **Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models**
**Institution:** Tencent AI Lab
|
[](http://arxiv.org/pdf/2401.08350v1)
[](summary/2023-02/2401.0835.md) |
|
01-15 | **A Study on Large Language Models' Limitations in Multiple-Choice Question Answering**
**Institution:** David R. Cheriton School of Computer Science
|
[](http://arxiv.org/pdf/2401.07955v1)
[](summary/2023-02/2401.07955.md) |
|
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
|
[](http://arxiv.org/pdf/2401.06477v1)
[](summary/2023-02/2401.06477.md) |
|
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
|
[](http://arxiv.org/pdf/2401.06373v1)
[](summary/2023-02/2401.06373.md) |
|
01-11 | **TOFU: A Task of Fictitious Unlearning for LLMs**
**Institution:** Carnegie Mellon University
|
[](http://arxiv.org/pdf/2401.06121v1)
[](summary/2023-02/2401.06121.md) |
|
01-11 | **LLM-as-a-Coauthor: The Challenges of Detecting LLM-Human Mixcase**
**Institution:** LAIR Lab Lehigh University, Huazhong University of Science and Technology
|
[](http://arxiv.org/pdf/2401.05952v1)
[](summary/2023-02/2401.05952.md) |
|
01-10 | **Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing**
**Institution:** Google Research
|
[](http://arxiv.org/pdf/2401.04881v1)
[](summary/2023-02/2401.04881.md) |
|
01-10 | **CASA: Causality-driven Argument Sufficiency Assessment**
**Institution:** Peking University
|
[](http://arxiv.org/pdf/2401.05249v1)
[](summary/2023-02/2401.05249.md) |
|
01-10 | **InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks**
|
[](http://arxiv.org/pdf/2401.05507v1)
[](summary/2023-02/2401.05507.md) |
|
01-09 | **Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search**
**Institution:** Nanyang Technological University Singapore
|
[](http://arxiv.org/pdf/2401.04514v1)
[](summary/2023-02/2401.04514.md) |
|
01-04 | **SPEER: Sentence-Level Planning of Long Clinical Summaries via Embedded Entity Retrieval**
**Institution:** Columbia University
|
[](http://arxiv.org/pdf/2401.02369v1)
[](summary/2023-02/2401.02369.md) |
|
01-02 | **LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning**
|
[](http://arxiv.org/pdf/2401.01325v1)
[](summary/2023-02/2401.01325.md) |
|