Automated-Fact-Checking-Resources  by Cartus

Fact-checking resources, links to publications

created 4 years ago
517 stars

Top 61.5% on sourcepulse

GitHubView on GitHub
Project Summary

This repository serves as a curated collection of resources for automated fact-checking (AFC), primarily stemming from two survey papers: "A Survey on Automated Fact-Checking" and "Multimodal Automated Fact-Checking: A Survey." It targets researchers and practitioners in NLP and AI interested in understanding and advancing the field of AFC, offering a structured overview of tasks, datasets, models, and relevant research.

How It Works

The repository organizes resources based on the established AFC pipeline: claim detection/extraction, evidence retrieval, and claim verification (including verdict prediction and justification production). It also categorizes related tasks like manipulation classification and out-of-context classification, reflecting the evolution of AFC to include multimodal and LLM-specific challenges. The structure aims to provide a comprehensive, up-to-date landscape of the AFC research domain.

Quick Start & Requirements

This repository is a collection of links to papers, datasets, and code. There are no direct installation or execution commands. Users will need to follow the links provided to access the individual resources.

Highlighted Details

  • Comprehensive coverage of text-based and multimodal AFC.
  • Regular updates with recent publications from major NLP/AI conferences (EMNLP, NeurIPS, ACL, etc.).
  • Detailed breakdown of tasks, including emerging areas like factuality in LLMs and detecting LLM-generated text.
  • Extensive lists of datasets and models with direct links to papers and, where available, code.

Maintenance & Community

The repository is actively maintained, with updates noted for December 2024 (adding LLM factuality) and August 2024 (adding papers from WWW, IJCAI, ACL).

Licensing & Compatibility

The repository itself is a collection of links and does not have a specific license. Individual resources (papers, datasets, code) will have their own licenses.

Limitations & Caveats

This repository is a curated list of external resources and does not provide any executable code or integrated tools for automated fact-checking itself. Users must navigate to the linked resources to utilize them.

Health Check
Last commit

5 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
32 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.