AIC CTU@AVerImaTeC: dual-retriever RAG for image-text fact checking

TL;DR

This paper introduces a simple yet effective dual-retriever RAG system for image-text fact checking, combining textual and image retrieval modules with a large language model, achieving competitive results at low cost.

Contribution

It presents a novel, easy-to-reproduce dual-retriever RAG pipeline integrating reverse image search with textual retrieval for fact checking.

Findings

Competitive performance with a single GPT5.1 call per fact check

Low average cost of $0.013 per fact check

Open-source code and resources provided for reproducibility

Abstract

In this paper, we present our 3rd place system in the AVerImaTeC shared task, which combines our last year's retrieval-augmented generation (RAG) pipeline with a reverse image search (RIS) module. Despite its simplicity, our system delivers competitive performance with a single multimodal LLM call per fact-check at just $0.013 on average using GPT5.1 via OpenAI Batch API. Our system is also easy to reproduce and tweak, consisting of only three decoupled modules - a textual retrieval module based on similarity search, an image retrieval module based on API-accessed RIS, and a generation module using GPT5.1 - which is why we suggest it as an accesible starting point for further experimentation. We publish its code and prompts, as well as our vector stores and insights into the scheme's running costs and directions for further improvement.