paper-with-me

홈 › Papers

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

2026-02-16 · Herbert Ullrich, Jan Drchal arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.15190

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalFact Checking

Similar Papers 제목 키워드 기반

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

2026-02-11 · Rui Cao, Zhenyun Deng, Yulong Chen, Michael Schlichtkrull 외 arxiv

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 e…

VILLAIN at AVerImaTeC: Verifying Image-Text Claims via Multi-Agent Collaboration

2026-02-04 · Jaeyoon Jung, Yejun Yoon, Kunwoo Park arxiv

This paper describes VILLAIN, a multimodal fact-checking system that verifies image-text claims through prompt-based multi-agent collaboration. For the AVerImaTeC shared task, VILLAIN employs vision-language model agents…

Adversarial Retriever-Ranker for dense text retrieval

2021-10-07 · ICLR 2022 4 · Hang Zhang, Yeyun Gong, Yelong Shen, Jiancheng Lv 외

Current dense text retrieval models face two typical challenges. First, they adopt a siamese dual-encoder architecture to encode queries and documents independently for fast indexing and searching, while neglecting the f…

Natural QuestionsRetrievalText RetrievalTriviaQA

Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation

2024-07-21 · Liwen Sun, James Zhao, Megan Han, Chenyan Xiong

Multimodal foundation models hold significant potential for automating radiology report generation, thereby assisting clinicians in diagnosing cardiac diseases. However, generated reports often suffer from serious factua…

DiagnosticRAGRetrievalText Generation

Decomposing Complex Queries for Tip-of-the-tongue Retrieval

2023-05-24 · Kevin Lin, Kyle Lo, Joseph E. Gonzalez, Dan Klein

When re-finding items, users who forget or are uncertain about identifying details often rely on creative strategies for expressing their information needs -- complex queries that describe content elements (e.g., book ch…

Retrieval