zjukg/KnowPAT

[Paper][ACL 2024 Findings] Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering

30
/ 100
Emerging

This project helps improve the quality of answers from Large Language Models (LLMs) when used for specific fields like finance or healthcare. It takes your existing questions, several possible answers, and your preferred ranking of those answers, then fine-tunes the LLM to provide better, more knowledgeable responses aligned with human judgment. This is useful for researchers and AI practitioners building specialized question-answering systems.

192 stars. No commits in the last 6 months.

Use this if you are a researcher or AI practitioner working to make LLMs give more accurate and domain-specific answers by incorporating external knowledge and human preferences.

Not ideal if you are a general user looking for an out-of-the-box LLM or if you don't have access to an existing LLM and a dataset of domain-specific questions with human-preferred answers.

domain-specific QA LLM fine-tuning knowledge graphs preference alignment AI research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

192

Forks

14

Language

Python

License

Last pushed

Jun 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/zjukg/KnowPAT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.