SOURCE-LINKED INTELLIGENCE

DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual understanding tasks such as chart and document question answering. However, existing benchmarks typically evaluate these domains in isolation, leaving underexplored a key capability: whether models can use textual context to determine how chart evidence should be selected, interpreted, and aggregated. We introduce DocHop, a benchmark for integrated chart--context reasoning in document-style images. In DocHop, the document narrative specifies multi-step compositional constraints, while charts provide

Read original source ↗ Open in workspace

recordType

paper

region

Global