RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Danni, Fan, Shaojing, Cheng, Harry, Kankanhalli, Mohan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910210837184512
author Xu, Danni
Fan, Shaojing
Cheng, Harry
Kankanhalli, Mohan
author_facet Xu, Danni
Fan, Shaojing
Cheng, Harry
Kankanhalli, Mohan
contents Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce \textbf{RW-Post}, a post-aligned \textbf{text--image benchmark} for real-world multimodal fact-checking with \emph{auditable} annotations: each instance links the original social-media post with reasoning traces and explicitly linked evidence items derived from human fact-check articles via an LLM-assisted extraction-and-auditing pipeline. RW-Post supports controlled evaluation across closed-book, evidence-bounded, and open-web regimes, enabling systematic diagnosis of visual grounding and evidence utilization. We provide \textbf{AgentFact} as a reference verification baseline and benchmark strong open-source LVLMs under unified protocols. Experiments show substantial headroom: current models struggle with faithful evidence grounding, while evidence-bounded evaluation improves both accuracy and faithfulness. Code and dataset will be released at https://github.com/xudanni0927/AgentFact.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10357
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
Xu, Danni
Fan, Shaojing
Cheng, Harry
Kankanhalli, Mohan
Multimedia
Artificial Intelligence
Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce \textbf{RW-Post}, a post-aligned \textbf{text--image benchmark} for real-world multimodal fact-checking with \emph{auditable} annotations: each instance links the original social-media post with reasoning traces and explicitly linked evidence items derived from human fact-check articles via an LLM-assisted extraction-and-auditing pipeline. RW-Post supports controlled evaluation across closed-book, evidence-bounded, and open-web regimes, enabling systematic diagnosis of visual grounding and evidence utilization. We provide \textbf{AgentFact} as a reference verification baseline and benchmark strong open-source LVLMs under unified protocols. Experiments show substantial headroom: current models struggle with faithful evidence grounding, while evidence-bounded evaluation improves both accuracy and faithfulness. Code and dataset will be released at https://github.com/xudanni0927/AgentFact.
title RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
topic Multimedia
Artificial Intelligence
url https://arxiv.org/abs/2605.10357