# QKVQA: Question-Focused Filtering for Knowledge-based VQA

arXiv: https://arxiv.org/abs/2601.13856 · HTML: https://mlsanity.com/paper/2601.13856/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jan 2026.

## Built on by (most cited first, 4 of 4)

- [ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering](https://mlsanity.com/paper/2606.27974/) (2026)
- [Look Twice: Training-Free Evidence Highlighting for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2604.01280/) (2026)
- [MMAgent-R2: Learning to Rerank and Reject for Agentic mRAG](https://mlsanity.com/paper/2607.07383/) (2026)
- [Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models](https://mlsanity.com/paper/2609.16795/) (2026)

## Abstract (arXiv)

Visual Question Answering (VQA) is the task of answering questions based on image content. Building upon this, Knowledge-Based VQA (KB-VQA) requires models to answer questions that depend on external knowledge beyond the visual content of an image. In such settings, effective knowledge filtering is essential for achieving high question answering accuracy. Typical filtering methods suffer from two issues: they fail to focus on parts relevant to the question during candidate section encoding, and they use similarity metrics to locate a section from a single article, resulting in information limitation. To address these issues, this paper proposes a question-focused, cross-article filtering method. Specifically, we design a trainable Question-Focused Filter (QFF) and a Chunk-based Dynamic Cross-Article Selection module (CDA). This approach maintains inference time comparable to the optimal method with the shorter context length, efficiently obtaining high-quality filtered knowledge. The accuracy outperforms current state-of-the-art methods by 3.2 and 2.2 percentage points on Encyclopedic-VQA and InfoSeek, respectively. The code is publicly available at: https://github.com/leaffeall/QKVQA.