opendilab/awesome-RLHF
An awesome list aggregating research papers, codebases, and datasets on Reinforcement Learning with Human Feedback for language model alignment.
Not currently ranked — collecting fresh signals.
star history
This repository compiles research papers and resources on Reinforcement Learning with Human Feedback (RLHF), a technique used to align large language models with human preferences. The collection is organized by year from 2020 to 2026 and includes codebases, datasets, blogs, and books relevant to the RLHF ecosystem. It serves as a reference for understanding how RLHF enables models like ChatGPT to better match complex human values.
Frequently asked
- What is opendilab/awesome-RLHF?
- An awesome list aggregating research papers, codebases, and datasets on Reinforcement Learning with Human Feedback for language model alignment.
- Is awesome-RLHF open source?
- Yes — opendilab/awesome-RLHF is open source, released under the Apache-2.0 license.
- How popular is awesome-RLHF?
- opendilab/awesome-RLHF has 4.4k stars on GitHub.
- Where can I find awesome-RLHF?
- opendilab/awesome-RLHF is on GitHub at https://github.com/opendilab/awesome-RLHF.