Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Wenyan, Xiang, Dawei, Ding, Tianqi, Lu, Weihai
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.25120
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912675895705600
author Xu, Wenyan
Xiang, Dawei
Ding, Tianqi
Lu, Weihai
author_facet Xu, Wenyan
Xiang, Dawei
Ding, Tianqi
Lu, Weihai
contents Misinformation and disinformation demand fact checking that goes beyond simple evidence-based reasoning. Existing benchmarks fall short: they are largely single modality (text-only), span short time horizons, use shallow evidence, cover domains unevenly, and often omit full articles -- obscuring models' real-world capability. We present MMM-Fact, a large-scale benchmark of 125,449 fact-checked statements (1995--2025) across multiple domains, each paired with the full fact-check article and multimodal evidence (text, images, videos, tables) from four fact-checking sites and one news outlet. To reflect verification effort, each statement is tagged with a retrieval-difficulty tier -- Basic (1--5 sources), Intermediate (6--10), and Advanced (>10) -- supporting fairness-aware evaluation for multi-step, cross-modal reasoning. The dataset adopts a three-class veracity scheme (true/false/not enough information) and enables tasks in veracity prediction, explainable fact-checking, complex evidence aggregation, and longitudinal analysis. Baselines with mainstream LLMs show MMM-Fact is markedly harder than prior resources, with performance degrading as evidence complexity rises. MMM-Fact offers a realistic, scalable benchmark for transparent, reliable, multimodal fact-checking.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25120
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MMM-Fact: A Multimodal, Multi-Domain Fact-Checking Dataset with Multi-Level Retrieval Difficulty
Xu, Wenyan
Xiang, Dawei
Ding, Tianqi
Lu, Weihai
Social and Information Networks
Misinformation and disinformation demand fact checking that goes beyond simple evidence-based reasoning. Existing benchmarks fall short: they are largely single modality (text-only), span short time horizons, use shallow evidence, cover domains unevenly, and often omit full articles -- obscuring models' real-world capability. We present MMM-Fact, a large-scale benchmark of 125,449 fact-checked statements (1995--2025) across multiple domains, each paired with the full fact-check article and multimodal evidence (text, images, videos, tables) from four fact-checking sites and one news outlet. To reflect verification effort, each statement is tagged with a retrieval-difficulty tier -- Basic (1--5 sources), Intermediate (6--10), and Advanced (>10) -- supporting fairness-aware evaluation for multi-step, cross-modal reasoning. The dataset adopts a three-class veracity scheme (true/false/not enough information) and enables tasks in veracity prediction, explainable fact-checking, complex evidence aggregation, and longitudinal analysis. Baselines with mainstream LLMs show MMM-Fact is markedly harder than prior resources, with performance degrading as evidence complexity rises. MMM-Fact offers a realistic, scalable benchmark for transparent, reliable, multimodal fact-checking.
title MMM-Fact: A Multimodal, Multi-Domain Fact-Checking Dataset with Multi-Level Retrieval Difficulty
topic Social and Information Networks
url https://arxiv.org/abs/2510.25120