A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

Open-source calculator for LLM system requirements.

open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality

Official code for the ACL 2024 paper: Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages.

I-SHEEP: Iterative Self-enHancEmEnt Paradigm of LLMs through Self-Instruct and Self-Assessment

Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication

A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

Open CS Application | 开源CS申请

Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

A repo lists papers related to LLM based agent

Knowledge Circuits in Pretrained Transformers

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

Accelerating the development of large multimodal models (LMMs) with lmms-eval

A recipe for online RLHF.

SimPO: Simple Preference Optimization with a Reference-Free Reward

Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"

Tutorials on training and testing retrieval-based models (DrQA & DPR)

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

Codes for our paper "RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation"