gao-g/prelude

Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".

⭐ 45 ⑂ 1 Python MIT · 2024-11-23推送

https://arxiv.org/pdf/2404.15269

alignment gpt4 llm llms transformers interpretability human-feedback edits preference-learning user-feedback

45

Watchers

0

贡献者

0

Commits

0

Releases

2

Open Issues

2024-11-23

最近推送

原文中文

暂无 README