RLHFlow / RAFTLinks
This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or rejection sampling fine-tuning.
☆32Updated 9 months ago
Alternatives and similar repositories for RAFT
Users that are interested in RAFT are comparing it to the libraries listed below
Sorting:
- Revisiting Mid-training in the Era of RL Scaling☆56Updated 2 months ago
- Directional Preference Alignment☆57Updated 9 months ago
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆37Updated last week
- Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)☆54Updated 7 months ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆63Updated 6 months ago
- ☆46Updated 7 months ago
- ☆46Updated 2 months ago
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆47Updated last month
- ☆59Updated 9 months ago
- ☆22Updated 11 months ago
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆62Updated 11 months ago
- ☆18Updated last year
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆73Updated last month
- Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆59Updated last week
- The rule-based evaluation subset and code implementation of Omni-MATH☆22Updated 6 months ago
- This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…☆25Updated 6 months ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆40Updated 9 months ago
- A Sober Look at Language Model Reasoning☆74Updated last week
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 9 months ago
- The code and data for the paper JiuZhang3.0☆46Updated last year
- This is the repo for our paper "Mr-Ben: A Comprehensive Meta-Reasoning Benchmark for Large Language Models"☆50Updated 7 months ago
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆30Updated last month
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆63Updated 7 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆60Updated 6 months ago
- ☆13Updated 11 months ago
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆108Updated 6 months ago
- ☆67Updated last year
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆99Updated last month
- Critique-out-Loud Reward Models☆66Updated 8 months ago
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆30Updated last year