TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning
We introduce TOPOGRAPHRAG-BENCH, a layout-grounded benchmark for multimodal evidence reasoning in GraphRAG, comprising 2,024 questions over 201 long, visually rich documents.
ProofPaper ↗
Key points
- Real-world documents distribute evidence across text, tables, figures, and captions within complex page layouts.
- Answering complex questions over such documents therefore requires more than retrieving relevant passages: systems must recover the evidence topology that connects heterogeneous evidence units.
- We evaluate text-only GraphRAG, page-level visual retrieval, and multimodal GraphRAG systems using retrieval, generation, and topology-aware reasoning metrics.
- These findings motivate GraphRAG systems that move beyond text-derived entity relation graphs to explicitly model document layouts, cross-modal evidence alignment, and the reasoning roles of evidence units.
Sources (1)
- [1]TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence ReasoningarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 03:15 AM
We introduce TOPOGRAPHRAG-BENCH, a layout-grounded benchmark for multimodal evidence reasoning in GraphRAG, comprising 2,024 questions over 201 long, visually rich documents.
Real-world documents distribute evidence across text, tables, figures, and captions within complex page layouts.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 6, 2026EmbeddingGemma 2: an open, lightweight multimodal embedding model
- Oct 6, 2026Build a voice travel concierge with Amazon Bedrock AgentCore, Managed Knowledge Base and Nova Sonic
- Oct 6, 2026Learning to Retrieve via Reinforcement Learning in Embedding Space
- Oct 2, 2026Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation
- Oct 1, 2026Barclays scales Claude to upgrade operations and improve client experience
- Jul 15, 2026huggingface/transformers v5.14.0: Release v5.14.0