# MAB-DQA: Addressing Query Aspect Importance in Document Question Answering with Multi-Armed Bandits

arXiv: https://arxiv.org/abs/2604.08952 · HTML: https://mlsanity.com/paper/2604.08952/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [RA-DIT: Retrieval-Augmented Dual Instruction Tuning](https://mlsanity.com/paper/2310.01352/) (2023)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating](https://mlsanity.com/paper/2412.18424/) (2024)
- [MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding](https://mlsanity.com/paper/2503.13964/) (2025)
- [UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis](https://mlsanity.com/paper/2406.15187/) (2024)
- [IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design](https://mlsanity.com/paper/2504.13176/) (2025)
- [MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity](https://mlsanity.com/paper/2412.01572/) (2024)
- [Adversarial Training Towards Robust Multimedia Recommender System](https://mlsanity.com/paper/1809.07062/) (2018)
- [Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check](https://mlsanity.com/paper/2403.18243/) (2024)
- [Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering](https://mlsanity.com/paper/2502.14245/) (2025)
- [DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2504.18243/) (2025)
- [MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval](https://mlsanity.com/paper/2509.07666/) (2025)
- [NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning](https://mlsanity.com/paper/2412.15547/) (2024)
- [Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering](https://mlsanity.com/paper/2502.11491/) (2025)
- [Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering](https://mlsanity.com/paper/2506.00491/) (2025)
- [ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision](https://mlsanity.com/paper/2505.21250/) (2025)
- [NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering](https://mlsanity.com/paper/2505.19754/) (2025)

## Abstract (arXiv)

Document Question Answering (DQA) involves generating answers from a document based on a user's query, representing a key task in document understanding. This task requires interpreting visual layouts, which has prompted recent studies to adopt multimodal Retrieval-Augmented Generation (RAG) that processes page images for answer generation. However, in multimodal RAG, visual DQA struggles to utilize a large number of images effectively, as the retrieval stage often retains only a few candidate pages (e.g., Top-4), causing informative but less visually salient content to be overlooked in favor of common yet low-information pages. To address this issue, we propose a Multi-Armed Bandit-based DQA framework (MAB-DQA) to explicitly model the varying importance of multiple implicit aspects in a query. Specifically, MAB-DQA decomposes a query into aspect-aware subqueries and retrieves an aspect-specific candidate set for each. It treats each subquery as an arm and uses preliminary reasoning results from a small number of representative pages as reward signals to estimate aspect utility. Guided by an exploration-exploitation policy, MAB-DQA dynamically reallocates retrieval budgets toward high-value aspects. With the most informative pages and their correlations, MAB-DQA generates the expected results. On four benchmarks, MAB-DQA shows an average improvement of 5%-18% over the state-of-the-art method, consistently enhancing document understanding. Codes are available at https://github.com/ElephantOH/MAB-DQA.