WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Yingjian, Wang, Xinming, Ding, Kun, Wang, Ying, Fan, Bin, Xiang, Shiming
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911591112376320
author Zhu, Yingjian
Wang, Xinming
Ding, Kun
Wang, Ying
Fan, Bin
Xiang, Shiming
author_facet Zhu, Yingjian
Wang, Xinming
Ding, Kun
Wang, Ying
Fan, Bin
Xiang, Shiming
contents Multi-modal Retrieval-Augmented Generation (RAG) has emerged as a highly effective paradigm for Knowledge-Based Visual Question Answering (KB-VQA). Despite recent advancements, prevailing methods still primarily depend on images as the retrieval key, and often overlook or misplace the role of Vision-Language Models (VLMs), thereby failing to leverage their potential fully. In this paper, we introduce WikiSeeker, a novel multi-modal RAG framework that bridges these gaps by proposing a multi-modal retriever and redefining the role of VLMs. Rather than serving merely as answer generators, we assign VLMs two specialized agents: a Refiner and an Inspector. The Refiner utilizes the capability of VLMs to rewrite the textual query according to the input image, significantly improving the performance of the multimodal retriever. The Inspector facilitates a decoupled generation strategy by selectively routing reliable retrieved context to another LLM for answer generation, while relying on the VLM's internal knowledge when retrieval is unreliable. Extensive experiments on EVQA, InfoSeek, and M2KR demonstrate that WikiSeeker achieves state-of-the-art performance, with substantial improvements in both retrieval accuracy and answer quality. Our code will be released on https://github.com/zhuyjan/WikiSeeker.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05818
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
Zhu, Yingjian
Wang, Xinming
Ding, Kun
Wang, Ying
Fan, Bin
Xiang, Shiming
Computer Vision and Pattern Recognition
Computation and Language
Information Retrieval
Multi-modal Retrieval-Augmented Generation (RAG) has emerged as a highly effective paradigm for Knowledge-Based Visual Question Answering (KB-VQA). Despite recent advancements, prevailing methods still primarily depend on images as the retrieval key, and often overlook or misplace the role of Vision-Language Models (VLMs), thereby failing to leverage their potential fully. In this paper, we introduce WikiSeeker, a novel multi-modal RAG framework that bridges these gaps by proposing a multi-modal retriever and redefining the role of VLMs. Rather than serving merely as answer generators, we assign VLMs two specialized agents: a Refiner and an Inspector. The Refiner utilizes the capability of VLMs to rewrite the textual query according to the input image, significantly improving the performance of the multimodal retriever. The Inspector facilitates a decoupled generation strategy by selectively routing reliable retrieved context to another LLM for answer generation, while relying on the VLM's internal knowledge when retrieval is unreliable. Extensive experiments on EVQA, InfoSeek, and M2KR demonstrate that WikiSeeker achieves state-of-the-art performance, with substantial improvements in both retrieval accuracy and answer quality. Our code will be released on https://github.com/zhuyjan/WikiSeeker.
title WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
topic Computer Vision and Pattern Recognition
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2604.05818