REVEAL: Retrieval-Enhanced Verification for Multimodal Fact-Checking

Amina Tariq, Yova Kementchedjhieva


Abstract
Multimodal misinformation combines images and text to amplify false narratives, yet most fact-checking research addresses only textualclaims. The AVerImaTeC shared task introduces real-world image-text claims requiring sophisticated evidence retrieval. We present REVEAL (Retrieval-Enhanced Verification with Evidence Accumulation Loop), a system designed to overcome the “semantic gap,” defined as the disconnect between the neutral phrasing of claims and the adversarial vocabulary of debunking evidence. Unlike static baselines, REVEAL breaks down the verification task into an iterative context loop, integrating sparse and dense retrieval signals to aggressively target refuting evidence. We achieve a Verdict Accuracy of 23.6% and an Evidence Recall of 27.7% on the test set. Our results outperform the official baseline across all metrics, validating our hybrid retrieval strategy for complex multimodal verification.
Anthology ID:
2026.fever-1.8
Volume:
Proceedings of the Ninth Fact Extraction and VERification Workshop (FEVER)
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Mubashara Akhtar, Rami Aly, Rui Cao, Christos Christodoulopoulos, Oana Cocarascu, Zhijiang Guo, Arpit Mittal, Michael Schlichtkrull, James Thorne, Andreas Vlachos
Venues:
FEVER | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
108–113
Language:
URL:
https://aclanthology.org/2026.fever-1.8/
DOI:
Bibkey:
Cite (ACL):
Amina Tariq and Yova Kementchedjhieva. 2026. REVEAL: Retrieval-Enhanced Verification for Multimodal Fact-Checking. In Proceedings of the Ninth Fact Extraction and VERification Workshop (FEVER), pages 108–113, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
REVEAL: Retrieval-Enhanced Verification for Multimodal Fact-Checking (Tariq & Kementchedjhieva, FEVER 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.fever-1.8.pdf