openai / safety-rbr-code-and-dataLinks
Code and example data for the paper: Rule Based Rewards for Language Model Safety
☆198Updated last year
Alternatives and similar repositories for safety-rbr-code-and-data
Users that are interested in safety-rbr-code-and-data are comparing it to the libraries listed below
Sorting:
- ☆100Updated last year
- ☆207Updated 6 months ago
- ☆192Updated 5 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆172Updated 2 months ago
- ☆99Updated 10 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆123Updated last year
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆141Updated last year
- RL Scaling and Test-Time Scaling (ICML'25)☆111Updated 8 months ago
- ☆318Updated 4 months ago
- ☆116Updated 8 months ago
- Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"☆171Updated 4 months ago
- ☆52Updated 4 months ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆245Updated 4 months ago
- Critique-out-Loud Reward Models☆70Updated 11 months ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆241Updated 11 months ago
- A simple unified framework for evaluating LLMs☆248Updated 5 months ago
- Self-playing Adversarial Language Game Enhances LLM Reasoning, NeurIPS 2024☆139Updated 7 months ago
- "Improving Mathematical Reasoning with Process Supervision" by OPENAI☆112Updated this week
- ☆211Updated 7 months ago
- Code for the paper: "Learning to Reason without External Rewards"☆357Updated 2 months ago
- ☆94Updated 4 months ago
- Self-Alignment with Principle-Following Reward Models☆166Updated 2 weeks ago
- A brief and partial summary of RLHF algorithms.☆132Updated 7 months ago
- ☆136Updated 10 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆164Updated 6 months ago
- official implementation of paper "Process Reward Model with Q-value Rankings"☆63Updated 7 months ago
- ☆206Updated 4 months ago
- ☆73Updated 6 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆172Updated 3 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆118Updated last year