用双检索器+大模型实现高效图文事实核查，成本仅1.3美分/次
AIC CTU@AVerImaTeC: dual-retriever RAG for image-text fact checking
- 采用文本与图像双检索模块，结合大模型生成判断结果
- 单次核查仅需一次多模态大模型调用，平均成本0.013美元
- 系统模块解耦易复现，适合初学者快速上手实验
本文介绍我们在 AVerImaTeC 共享任务中的第三名系统，该系统将去年的检索增强生成（RAG）流程与反向图像搜索（RIS）模块结合。尽管结构简单，其性能仍具竞争力：每次事实核查仅需一次多模态大模型调用，平均成本为0.013美元（使用GPT5.1通过OpenAI Batch API）。系统由三个独立模块构成——基于相似性搜索的文本检索模块、基于API调用的图像检索模块、以及使用GPT5.1的生成模块——具备良好的可复现性与可调性，适合作为后续研究的起点。我们公开了代码、提示模板、向量库，以及运行成本分析和改进方向建议。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。