Alternatives and similar repositories for chain-of-thought

Users that are interested in chain-of-thought are comparing it to the libraries listed below

• WHGTyen / BIG-Bench-Mistake
  A dataset of LLM-generated chain-of-thought steps annotated with mistake location.
  ☆82Updated last year
• Anni-Zou / DocBench
  DocBench: A Benchmark for Evaluating LLM-based Document Reading Systems
  ☆53Updated last year
• hyintell / awesome-refreshing-llms
  EMNLP'23 survey: a curation of awesome papers and resources on refreshing large language models (LLMs) without expensive retraining.
  ☆136Updated last year
• ryokamoi / llm-self-correction-papers
  List of papers on Self-Correction of LLMs.
  ☆80Updated 10 months ago
• ZitongYang / Synthetic_Continued_Pretraining
  Code implementation of synthetic continued pretraining
  ☆137Updated 10 months ago
• OFA-Sys / DiverseEvol
  Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
  ☆85Updated last year
• OpenMatch / ThinkNote
  This is the code repo for our paper "Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognitio…
  ☆109Updated last month
• Hannibal046 / xRAG
  [Neurips2024] Source code for xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
  ☆157Updated last year
• clinicalml / co-llm
  Co-LLM: Learning to Decode Collaboratively with Multiple Language Models
  ☆122Updated last year
• TIGER-AI-Lab / MAmmoTH2
  Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]
  ☆149Updated last year
• ernie-research / Tool-Augmented-Reward-Model
  [ICLR'24 spotlight] Tool-Augmented Reward Modeling
  ☆51Updated 5 months ago
• abhika-m / FAVA
  ☆74Updated last year
• weizhepei / InstructRAG
  [ICLR 2025] InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
  ☆128Updated 9 months ago
• fangyuan-ksgk / CoT-Reasoning-without-Prompting
  Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting
  ☆33Updated last year
• SqueezeAILab / LLM2LLM
  [ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
  ☆190Updated last year
• RUC-NLPIR / OmniEval
  Open source code of the paper: "OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain"
  ☆76Updated 10 months ago
• qhjqhj00 / WebBrain
  ☆68Updated 2 years ago
• TableBench / TableBench
  Official repository for paper "TableBench: A Comprehensive and Complex Benchmark for Table Question Answering"
  ☆74Updated 6 months ago
• ByteDance-Seed / WideSearch
  WideSearch: Benchmarking Agentic Broad Info-Seeking
  ☆98Updated last month
• fairyshine / Seal-Tools
  The source code and dataset mentioned in the paper Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmar…
  ☆51Updated last year
• yifanzhang-pro / AutoMathText
  [ACL 2025 Findings] Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts (As Huggingface Daily Papers: …
  ☆88Updated 2 months ago
• DAMO-NLP-SG / contrastive-cot
  Contrastive Chain-of-Thought Prompting
  ☆68Updated last year
• GAIR-NLP / ProX
  [ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
  ☆263Updated 4 months ago
• DataArcTech / LLM-as-a-Judge
  ☆151Updated 3 weeks ago
• tigerchen52 / awesome_role_of_small_models
  a curated list of the role of small models in the LLM era
  ☆107Updated last year
• yueyu1030 / AttrPrompt
  [NeurIPS 2023] This is the code for the paper `Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias`.
  ☆155Updated 2 years ago
• Quehry / HelloBench
  HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
  ☆52Updated 11 months ago
• kaistAI / Janus
  [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages
  ☆51Updated 3 months ago
• dongguanting / DPA-RAG
  The code and data of DPA-RAG, accepted by WWW 2025 main conference.
  ☆63Updated 2 weeks ago
• LuJunru / MemoChat
  MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation
  ☆28Updated last year