ryokamoi / llm-self-correction-papersLinks
List of papers on Self-Correction of LLMs.
☆81Updated last year
Alternatives and similar repositories for llm-self-correction-papers
Users that are interested in llm-self-correction-papers are comparing it to the libraries listed below
Sorting:
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆85Updated last year
- [NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI☆107Updated 9 months ago
- ☆75Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- Scalable Meta-Evaluation of LLMs as Evaluators☆43Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆77Updated last year
- CodeUltraFeedback: aligning large language models to coding preferences (TOSEM 2025)☆73Updated last year
- Astraios: Parameter-Efficient Instruction Tuning Code Language Models☆63Updated last year
- In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning☆35Updated 2 years ago
- Verifiers for LLM Reinforcement Learning☆80Updated 8 months ago
- ☆67Updated 9 months ago
- ☆64Updated last year
- Source code for GreaTer ICLR 2025 - Gradient Over Reasoning makes Smaller Language Models Strong Prompt Optimizers☆34Updated 8 months ago
- 🚢 Data Toolkit for Sailor Language Models☆95Updated 10 months ago
- Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators (Liu et al.; COLM 2024)☆48Updated 11 months ago
- ☆129Updated last year
- ☆150Updated last year
- ☆51Updated last year
- [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages☆52Updated 4 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆62Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆45Updated 2 months ago
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated 10 months ago
- Codebase for Instruction Following without Instruction Tuning☆36Updated last year
- Reformatted Alignment☆112Updated last year
- Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…☆58Updated last week
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆149Updated last year
- Codebase accompanying the Summary of a Haystack paper.☆80Updated last year
- Code for ACL2023 paper: Pre-Training to Learn in Context☆106Updated last year
- Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorch☆28Updated last week
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆51Updated 6 months ago