BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence

• URL: http://arxiv.org/abs/2603.07931v1
• Date: Mon, 09 Mar 2026 03:54:08 GMT
• Title: BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence
• Abstract summary: We introduce BRIDGE, a benchmark for multi-hop reasoning over long scientific papers.<n>The dataset supports both chain-like and fan-out structures and provides explicit multi-hop reasoning annotations.
• Score: 19.79339768762567
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook intermediate reasoning, especially in long multimodal documents. We introduce BRIDGE, a benchmark for multi-hop reasoning over long scientific papers that require integrating evidence across text, tables, and figures. The dataset supports both chain-like and fan-out structures and provides explicit multi-hop reasoning annotations for step-level evaluation beyond answer accuracy. Experiments with state-of-the-art LLMs and multimodal retrieval-augmented generation (RAG) systems reveal systematic deficiencies in evidence aggregation and grounding that remain hidden under conventional answer-only evaluation. BRIDGE provides a targeted testbed for diagnosing reasoning failures in long multimodal documents.

Related papers

• CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation [15.857678905969273]
  CrossModalQA is an open-domain benchmark for evaluating multimodal retrieval and reasoning over heterogeneous corpora.<n>It covers five complementary reasoning paths: vision-to-text, text-to-vision, vision-to-text-to-vision, multi-image intersection, and image-set reasoning.
  arXiv  Detail & Related papers  (2026-08-31T16:00:59Z)
• Multimodal Fact-Level Attribution for Verifiable Reasoning [80.60864342985748]
  Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation.<n>Existing multimodal grounding benchmarks and evaluation methods fail to assess attribution in complex multimodal reasoning.<n>We introduce MuRGAt, a benchmark for evaluating fact-level multimodal attribution in settings that require reasoning beyond direct observation.
  arXiv  Detail & Related papers  (2026-02-12T03:10:02Z)
• MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering [51.19392014547221]
  Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures.<n>Current approaches rely on query-agnostic document representations that overlook salient content.<n>We propose the Multimodal Adaptive Retrieval-Augmented (MARA) framework, which introduces query-adaptive generation.
  arXiv  Detail & Related papers  (2026-02-01T12:27:40Z)
• Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding [49.26132236798123]
  Vision Language Models (VLMs) have gradually become a primary approach in document understanding.<n>We propose SLEUTH, a multi agent framework that orchestrates a retriever and four collaborative agents in a coarse to fine process.<n>The framework identifies key textual and visual clues within the retrieved pages, filters for salient visual evidence such as tables and charts, and analyzes the query to devise a reasoning strategy.
  arXiv  Detail & Related papers  (2025-11-28T03:09:40Z)
• MAVIS: A Benchmark for Multimodal Source Attribution in Long-form Visual Question Answering [44.41273615523289]
  We introduce MAVIS, the first benchmark designed to evaluate multimodal source attribution systems.<n>Our dataset comprises 157K visual QA instances, where each answer is annotated with fact-level citations referring to multimodal documents.<n>We develop fine-grained automatic metrics along three dimensions of informativeness, groundedness, and fluency, and demonstrate their strong correlation with human judgments.
  arXiv  Detail & Related papers  (2025-11-15T10:14:59Z)
• DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections [23.428084176322866]
  We propose DocHop-QA, a large-scale benchmark for multimodal, multi-document, multi-hop question answering.<n> DocHop-QA is domain-agnostic and incorporates diverse information formats, including textual passages, tables, and structural layout cues.<n>We evaluate DocHop-QA through four tasks spanning structured index prediction, generative answering, and multimodal integration.
  arXiv  Detail & Related papers  (2025-08-20T08:17:45Z)
• DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding [66.07724324530844]
  We propose DocThinker, a rule-based Reinforcement Learning framework for dynamic inference-time reasoning.<n>Our method mitigates catastrophic forgetting and enhances both adaptability and transparency.<n>Our findings highlight RL as a powerful alternative for enhancing explainability and adaptability in MLLM-based document understanding.
  arXiv  Detail & Related papers  (2025-08-12T03:06:55Z)
• MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks [56.350173737493215]
  Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency.<n>MMESGBench is a first-of-its-kind benchmark dataset to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents.<n>MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories.
  arXiv  Detail & Related papers  (2025-07-25T03:58:07Z)
• MultiHoax: A Dataset of Multi-hop False-Premise Questions [10.301985230669684]
  We introduce MultiHoax, a benchmark for evaluating Large Language Models' ability to handle false premises in complex, multi-step reasoning tasks.<n>Our dataset spans seven countries and ten diverse knowledge categories, using Wikipedia as the primary knowledge source.<n> Experiments reveal that state-of-the-art LLMs struggle to detect false premises across different countries, knowledge categories, and multi-hop reasoning types.
  arXiv  Detail & Related papers  (2025-05-30T21:55:18Z)
• Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering [60.062194349648195]
  Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents.<n>Current document retrieval-augmented generation (DocRAG) methods remain limited by their text-centric approaches.<n>We introduce MMDocRAG, a comprehensive benchmark featuring 4,055 expert-annotated QA pairs with multi-page, cross-modal evidence chains.
  arXiv  Detail & Related papers  (2025-05-22T09:52:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.