ssu-humane/HerO
The code for HerO: a fact-checking pipeline based on open LLMs (the runner-up in AVeriTeC)
This project helps fact-checkers and disinformation analysts verify real-world claims by sifting through web evidence. You input a specific claim, and the system retrieves relevant information, generates questions to verify facts, and ultimately provides a verdict on the claim's truthfulness with an explanation. It's designed for anyone needing to quickly and accurately assess the veracity of statements, particularly those dealing with a high volume of information.
No commits in the last 6 months.
Use this if you need an automated pipeline to help verify claims by retrieving evidence from the web and predicting veracity using open-source large language models.
Not ideal if you require a system that operates without relying on large language models or if you prefer a human-only verification process.
Stars
14
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ssu-humane/HerO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GAIR-NLP/factool
FacTool: Factuality Detection in Generative AI
multimodal-ai-lab/DEFAME
Fact-checking system for textual and visual inputs.
BharathxD/ClaimeAI
This AI fact-checking system, built with LangGraph, dissects text into verifiable claims,...
TimLukaHorstmann/T-REX
Real-time fact-checking of tabular claims with SOTA reasoning LLMs.
iacobp/fact-checker
This tool allows Perplexity Pro users to fact-check selected text on any webpage, providing...