ictnlp/TruthX

Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"

34
/ 100
Emerging

This helps users get more accurate and truthful responses from Large Language Models (LLMs) like Llama-2. It takes an existing LLM and enhances its ability to provide factual information, reducing 'hallucinations' or made-up details. The output is a more reliable LLM that can be directly used for various tasks, benefiting anyone who uses LLMs for information retrieval or content generation, such as researchers, content creators, or customer support teams.

143 stars. No commits in the last 6 months.

Use this if you need to significantly improve the factual accuracy and reduce errors in information generated by a Large Language Model.

Not ideal if your primary concern is generating highly creative, imaginative, or fictional content where factual accuracy is secondary.

LLM-safety fact-checking AI-content-generation knowledge-retrieval natural-language-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

143

Forks

7

Language

Python

License

GPL-3.0

Last pushed

Mar 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ictnlp/TruthX"

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