CyberAgentAILab / regularized-bonLinks
Code of "Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment" (2025).
☆14Updated 2 months ago
Alternatives and similar repositories for regularized-bon
Users that are interested in regularized-bon are comparing it to the libraries listed below
Sorting:
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆57Updated 4 months ago
- Codebase for Instruction Following without Instruction Tuning☆34Updated 9 months ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆40Updated 9 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆95Updated 2 weeks ago
- This the implementation of LeCo☆31Updated 5 months ago
- Revisiting Mid-training in the Era of RL Scaling☆62Updated 2 months ago
- An Open Math Pre-trainng Dataset with 370B Tokens.☆89Updated 2 months ago
- [ICLR 2025] LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization☆37Updated 4 months ago
- Exploring Model Kinship for Merging Large Language Models☆24Updated 2 months ago
- ☆52Updated 4 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆72Updated 3 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
- ☆78Updated last month
- ☆12Updated 11 months ago
- ☆18Updated last year
- ☆97Updated last year
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆32Updated 9 months ago
- ☆47Updated 2 weeks ago
- ☆40Updated 2 weeks ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆110Updated 8 months ago
- ☆14Updated last year
- ☆53Updated last week
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆54Updated last year
- A repo for open research on building large reasoning models☆34Updated last week
- ☆17Updated 2 months ago
- Code for "Reasoning to Learn from Latent Thoughts"☆105Updated 2 months ago
- This repo is reproduction resources for linear alignment paper, still working☆17Updated last year
- The code and data for the paper JiuZhang3.0☆47Updated last year
- [NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study☆51Updated 7 months ago