Skip to content
Herbert Ullrich
Go back

Claim Extraction for Fact-Checking: Data, Models, and Automated Metrics

Edit page

Authors: H Ullrich, T Mlynář, J Drchal
Venue: arXiv preprint arXiv:2502.04955
Year: 2025
Citations: 2

Abstract

The work examines claim extraction as a dedicated subtask for fact-checking, introducing data, modeling strategies, and automatic metrics tailored to claim quality. It analyzes the trade-off between extracting many candidate claims and extracting claims that are specific, verifiable, and useful downstream.

Resources

Notes

In practice, this paper helped us treat claim extraction as a first-class modeling problem rather than a preprocessing detail. Better claim quality noticeably improved retrieval focus and final verification reliability in later pipelines.


Edit page
Share this post on:

Previous Post
🥇 AIC CTU@FEVER 8: On-premise fact checking through long context RAG
Next Post
Pipeline and dataset generation for automated fact-checking in almost any language