[ICML2022] G-Mixup: Graph Data Augmentation for Graph Classification

ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

RewardBench: the first evaluation tool for reward models.

PIM through Azure portal is slow and cannot be automated. This repo tries to implement a CLI version that is based on mainly REST API and AZCLI This code borrowed insights from other repos: https:/…

The MATH Dataset (NeurIPS 2021)

HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

Large-scale pretrained models for goal-directed dialog

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Let ChatGPT teach your own chatbot in hours with a single GPU!

Specify what you want it to build, the AI asks for clarification, and then builds it. Completely separate team and codebase from the AI Web App builder https://gptengineer.app

Large datasets for conversational AI

🌲 Code for our EMNLP 2023 paper - 🎄 "Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models"

This is a repository for sharing papers in the field of empathetic conversational AI. The related source code for each paper is linked if available.

ClariQ: SCAI Workshop data challenge on conversational search clarification.

Proactive Dialogue Systems - Paper Reading List

AvaTaR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval (https://arxiv.org/abs/2406.11200)

Forward-Looking Active REtrieval-augmented generation (FLARE)

The official implementation of the ICML 2024 paper "MemoryLLM: Towards Self-Updatable Large Language Models"

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases (https://stark.stanford.edu/)

All things prompt engineering

Early release of the official implementation for "GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts"

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

All-In-One VLM: Image + Video + Transfer to Other Languages / Domains (TPAMI 2023)

Flickr30K Entities Dataset