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

Source: [BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence](<https://www.sota2.com/research/paper/69afa5932d603e6de3e43bb8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-11T05:00:11.798Z

Authors: Biao Xiang, Soyeon Caren Han, Yihao Ding

Published: 2026-03-09T03:54:08.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.07931>)

[PDF](<https://arxiv.org/pdf/2603.07931.pdf>)
