Year: 2026
Type: conference-paper
Abstract: This paper presents an efficiency-aware pipeline for automated fact-checking of realworld image-text claims that treats multimodality as a controllable design variable rather than a property that must be uniformly propagated through every stage of the system.The approach decomposes claims into verification questions, assigns each to text-or image-related types, and applies modality-aware retrieval strategies, while ultimately relying on text-only evidence for verdict prediction and justification generation.Evaluated on the AVerImaTeC dataset within the FEVER-9 shared task, the system achieves competitive scores and ranks fourth overall, outperforming the official baseline on Evidence Score (0.2703 vs. 0.1707), Verdict Accuracy (0.2557 vs. 0.1136), and Justification Score (0.198 vs. 0.1322).These results demonstrate that strong performance on multimodal fact-checking can be achieved by selectively controlling where visual information influences retrieval and reasoning, rather than performing full multimodal fusion at every stage of the pipeline.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7140076415