dhfbk/faina
Fine-grained Fallacy Detection with Human Label Variation (NAACL 2025)
This project offers a specialized dataset and models for identifying different kinds of logical fallacies in social media posts. It takes Italian social media text as input and helps identify specific fallacies, even when human experts might disagree. Researchers and analysts focused on understanding and combating misinformation, particularly in Italian online discussions, would use this.
No commits in the last 6 months.
Use this if you need to analyze Italian social media text to automatically detect and categorize logical fallacies, especially if you're interested in how human experts might interpret the same text differently.
Not ideal if your primary goal is to analyze English text or if you need a simple 'true/false' fallacy detection without fine-grained categorization or consideration of annotator disagreement.
Stars
5
Forks
—
Language
Python
License
—
Category
Last pushed
Sep 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/dhfbk/faina"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mihail911/fake-news
Building a fake news detector from initial ideation to model deployment
google-research/fool-me-twice
Game code and data for Fool Me Twice: Entailment from Wikipedia Gamification...
FakeNewsChallenge/fnc-1-baseline
A baseline implementation for FNC-1
palewire/storysniffer
Inspect a URL and estimate if it contains a news story
IKMLab/CFEVER-data
AAAI-24 CFEVER: A Chinese Fact Extraction and VERification Dataset