ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering

2026-09-02

AI Summary

ViSAR通过在嵌入空间中构建查询条件页面级相似度矩阵，动态决定检索页面数量，解决了固定top-k检索方法导致的LVLM延迟增加和答案准确性下降问题。

Abstract

Document Visual Question Answering (DocVQA) often leverages Retrieval-Augmented Generation (RAG), where late-interaction encoders are commonly used to identify document pages relevant to a user query, before answer generation by a Large Vision-Language Model (LVLM). Existing approaches typically retrieve a fixed top-$k$ number of pages regardless of query complexity, which increases LVLM latency and may degrade answer accuracy. We introduce ViSAR (Visual Semantic Activation Retrieval), a training-free adaptive-$k$ retrieval method for late-interaction visual document retrieval. ViSAR operates directly in the embedding space to construct a query-conditioned page-level similarity matrix that highlights query-relevant semantics and dynamically determines the number of pages to retrieve. Across multiple encoders and LVLMs, ViSAR retrieves compact, query-adapted page sets that reduce RAG latency by up to 58.7\%, while maintaining or improving answer accuracy compared with fixed top-$k$ and adaptive retrieval heuristics. Furthermore, we show that the similarity matrix structure correlates with answer accuracy, suggesting future directions for retrieval quality-aware document understanding.

Problem

• DocVQA
• Retrieval-Augmented Generation
• Large Vision-Language Model
• adaptive retrieval
• query complexity

Innovation

• Training-Free
• Adaptive-$k$ Retrieval
• Similarity Matrix
• Late-Interaction
• Visual Document Question Answering