The Automatic Verification of Image-Text Claims (AVerImaTeC) Shared Task

TL;DR

This paper presents the AVerImaTeC shared task focused on developing systems for verifying image-text claims by retrieving evidence, with all submissions outperforming the baseline and the winning team achieving a score of 0.5455.

Contribution

It introduces a new shared task for automatic verification of image-text claims, providing a benchmark and detailed evaluation of current system capabilities.

Findings

All participating systems outperformed the baseline.

The winning team achieved an AVerImaTeC score of 0.5455.

Key insights and lessons learned from the shared task.

Abstract

The Automatic Verification of Image-Text Claims (AVerImaTeC) shared task aims to advance system development for retrieving evidence and verifying real-world image-text claims. Participants were allowed to either employ external knowledge sources, such as web search engines, or leverage the curated knowledge store provided by the organizers. System performance was evaluated using the AVerImaTeC score, defined as a conditional verdict accuracy in which a verdict is considered correct only when the associated evidence score exceeds a predefined threshold. The shared task attracted 14 submissions during the development phase and 6 submissions during the testing phase. All participating systems in the testing phase outperformed the baseline provided. The winning team, HUMANE, achieved an AVerImaTeC score of 0.5455. This paper provides a detailed description of the shared task, presents the complete evaluation results, and discusses key insights and lessons learned.