WeiXiongUST / Building-Math-Agents-with-Multi-Turn-Iterative-Preference-LearningLinks
This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DPO and KTO.
☆30Updated 10 months ago
Alternatives and similar repositories for Building-Math-Agents-with-Multi-Turn-Iterative-Preference-Learning
Users that are interested in Building-Math-Agents-with-Multi-Turn-Iterative-Preference-Learning are comparing it to the libraries listed below
Sorting:
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆123Updated last year
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆196Updated 6 months ago
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆37Updated last year
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆115Updated 10 months ago
- GenRM-CoT: Data release for verification rationales☆67Updated last year
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆178Updated 5 months ago
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆31Updated last year
- Reference implementation for Token-level Direct Preference Optimization(TDPO)