Facts are Harder Than Opinions -- A Multilingual, Comparative Analysis of LLM-Based Fact-Checking Reliability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Saju, Lorraine, Bleier, Arnim, Lasser, Jana, Wagner, Claudia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914105602867200
author Saju, Lorraine
Bleier, Arnim
Lasser, Jana
Wagner, Claudia
author_facet Saju, Lorraine
Bleier, Arnim
Lasser, Jana
Wagner, Claudia
contents The proliferation of misinformation necessitates scalable, automated fact-checking solutions. Yet, current benchmarks often overlook multilingual and topical diversity. This paper introduces a novel, dynamically extensible data set that includes 61,514 claims in multiple languages and topics, extending existing datasets up to 2024. Through a comprehensive evaluation of five prominent Large Language Models (LLMs), including GPT-4o, GPT-3.5 Turbo, LLaMA 3.1, and Mixtral 8x7B, we identify significant performance gaps between different languages and topics. While overall GPT-4o achieves the highest accuracy, it declines to classify 43% of claims. Across all models, factual-sounding claims are misclassified more often than opinions, revealing a key vulnerability. These findings underscore the need for caution and highlight challenges in deploying LLM-based fact-checking systems at scale.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03655
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Facts are Harder Than Opinions -- A Multilingual, Comparative Analysis of LLM-Based Fact-Checking Reliability
Saju, Lorraine
Bleier, Arnim
Lasser, Jana
Wagner, Claudia
Computers and Society
Computation and Language
The proliferation of misinformation necessitates scalable, automated fact-checking solutions. Yet, current benchmarks often overlook multilingual and topical diversity. This paper introduces a novel, dynamically extensible data set that includes 61,514 claims in multiple languages and topics, extending existing datasets up to 2024. Through a comprehensive evaluation of five prominent Large Language Models (LLMs), including GPT-4o, GPT-3.5 Turbo, LLaMA 3.1, and Mixtral 8x7B, we identify significant performance gaps between different languages and topics. While overall GPT-4o achieves the highest accuracy, it declines to classify 43% of claims. Across all models, factual-sounding claims are misclassified more often than opinions, revealing a key vulnerability. These findings underscore the need for caution and highlight challenges in deploying LLM-based fact-checking systems at scale.
title Facts are Harder Than Opinions -- A Multilingual, Comparative Analysis of LLM-Based Fact-Checking Reliability
topic Computers and Society
Computation and Language
url https://arxiv.org/abs/2506.03655