gao-g/prelude
Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".
This project helps AI developers and researchers refine how large language models (LLMs) learn user preferences. It takes in pairs of initial LLM outputs and subsequent user edits, then outputs an improved LLM agent that better anticipates user preferences. Developers working on LLM applications like summarization or email drafting would use this to make their models more aligned with human expectations.
No commits in the last 6 months.
Use this if you are developing or fine-tuning LLM agents and need a systematic way to incorporate user feedback and edits into their learning process.
Not ideal if you are an end-user looking for a ready-to-use application, as this project requires development expertise to implement and integrate agents.
Stars
45
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/gao-g/prelude"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.