Can LLMs Extract Human-like Fine-grained Evidence for Evidence-based Fact-checking?

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0201605" target="_blank" >RIV/00216305:26230/26:0201605 - isvavai.cz</a>

Result on the web

<a href="https://raslan2025.nlp-consulting.net/" target="_blank" >https://raslan2025.nlp-consulting.net/</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Can LLMs Extract Human-like Fine-grained Evidence for Evidence-based Fact-checking?

Original language description

Misinformation frequently spreads in user comments under online news articles, highlighting the need for effective methods to detect factually incorrect information. To strongly support or refute claims extracted from such comments, it is necessary to identify relevant documents and pinpoint the exact text spans that justify or contradict each claim. This paper focuses on the latter task --- fine-grained evidence extraction for Czech and Slovak claims. We create new dataset, containing two-way annotated fine-grained evidence created by paid annotators. We evaluate large language models (LLMs) on this dataset to assess their alignment with human annotations. The results reveal that LLMs often fail to copy evidence verbatim from the source text, leading to invalid outputs. Error-rate analysis shows that the llama3.1:8b model achieves a high proportion of correct outputs despite its relatively small size, while the gpt-oss-120b model underperforms despite having many more parameters. Furthermore, the models qwen3:14b, deepseek-r1:32b, and gpt-oss:20b demonstrate an effective balance between model size and alignment with human annotations.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/TQ16000028" target="_blank" >TQ16000028: FactDeMice – Evidence-based Fact-Checking with Fact-consistent translation, Fake Review Detection, and Automatic Misinformative Claim Extraction</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the Nineteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2025

ISBN

978-80-263-1858-3

ISSN

2336-4289

e-ISSN

—

Number of pages

11

Pages from-to

25-36

Publisher name

—

Place of publication

—

Event location

Borovets

Event date

Feb 16, 2005

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—