RLHFlow / RAFT
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.
☆29Updated 7 months ago
Alternatives and similar repositories for RAFT
Users that are interested in RAFT are comparing it to the libraries listed below
Sorting:
- Directional Preference Alignment☆57Updated 7 months ago
- This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…☆25Updated 5 months ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆61Updated 5 months ago
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆50Updated last year
- Revisiting Mid-training in the Era of RL Scaling☆37Updated 3 weeks ago
- ☆59Updated 8 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 8 months ago
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆30Updated 10 months ago
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆31Updated last month
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆74Updated 11 months ago
- Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)☆51Updated 6 months ago
- ☆45Updated 6 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆58Updated 4 months ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆40Updated 7 months ago
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆61Updated 10 months ago
- ☆13Updated 10 months ago
- [ACL 2024 Findings] CriticBench: Benchmarking LLMs for Critique-Correct Reasoning☆24Updated last year
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆48Updated 6 months ago
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".☆77Updated 4 months ago
- Domain-specific preference (DSP) data and customized RM fine-tuning.☆25Updated last year
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆47Updated 4 months ago
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆18Updated last month
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆55Updated 10 months ago
- BeHonest: Benchmarking Honesty in Large Language Models☆31Updated 9 months ago
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style☆40Updated last month
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆52Updated 2 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated last month
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆16Updated 4 months ago
- Code for ACL2024 paper - Adversarial Preference Optimization (APO).☆54Updated 11 months ago
- ☆40Updated last year