paper-with-me

홈 › Papers

MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering

2026-02-01 · Hui Wu, Haoquan Zhai, Yuchen Li, Hengyi Cai, Peirong Zhang, Yidan Zhang, Lei Wang, Chunle Wang, Yingyan Hou, Shuaiqiang Wang, Dawei Yin arxiv

Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmented generation (RAG) has shown strong performance in text-based QA, its extensions to multimodal documents remain underexplored and face significant limitations. Specifically, current approaches rely on query-agnostic document representations that overlook salient content and use static top-k evidence selection, which fails to adapt to the uncertain distribution of relevant information. To address these limitations, we propose the Multimodal Adaptive Retrieval-Augmented (MARA) framework, which introduces query-adaptive mechanisms to both retrieval and generation. MARA consists of two components: a Query-Aligned Region Encoder that builds multi-level document representations and reweights them based on query relevance to improve retrieval precision; and a Self-Reflective Evidence Controller that monitors evidence sufficiency during generation and adaptively incorporates content from lower-ranked sources using a sliding-window strategy. Experiments on six multimodal QA benchmarks demonstrate that MARA consistently improves retrieval relevance and answer quality over existing SOTA method.

📄 PDF Abstract BibTeX arXiv:2604.16313

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning

2025-02-25 · Runzhong Wang, Rui-Xi Wang, Mrunali Manjrekar, Connor W. Coley

Molecular machine learning has gained popularity with the advancements of geometric deep learning. In parallel, retrieval-augmented generation has become a principled approach commonly used with language models. However,…

Graph MatchingRetrievalRetrieval-augmented Generation

AgriGov: A Structured Multilingual Dataset Curation for Indian Government Schemes for Farmers

2026-06-06 · Mohsina Bilal, Gopakumar G arxiv

AgriGov is a curated, trilingual (English-Hindi-Marathi) dataset designed to address the scarcity of domain-grounded multilingual resources for agricultural policies and farmer welfare schemes. Initially, we collected an…

Information RetrievalMachine TranslationQuestion Answering

RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training

2024-10-18 · Muhe Ding, Yang Ma, Pengda Qin, Jianlong Wu 외

Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. MLLMs involve significant external k…

DenoisingQuestion AnsweringRetrieval

MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction

2025-02-05 · Xiao Hu, Eric Liu, Weizhou Wang, Xiangyu Guo 외

Retrieval-Augmented Generation (RAG) offers a solution to mitigate hallucinations in Large Language Models (LLMs) by grounding their outputs to knowledge retrieved from external sources. The use of private resources and …

Adversarial AttackRAGRetrievalRetrieval-augmented Generation

MARAGS: A Multi-Adapter System for Multi-Task Retrieval Augmented Generation Question Answering

2024-09-05 · Mitchell DeHaven

In this paper we present a multi-adapter retrieval augmented generation system (MARAGS) for Meta's Comprehensive RAG (CRAG) competition for KDD CUP 2024. CRAG is a question answering dataset contains 3 different subtasks…

Question AnsweringRAGRetrievalRetrieval-augmented Generation+1