Research map / Vision-language and multimodal / Multimodal LLMs
HighlightBench: Benchmarking and Diagnosing Markup-Driven Table Reasoning in Scientific Documents
Lexin Wang, Shenghua Liu, Yiwei Wang, Yujun Cai, Yuyao Ge, Jiayu Yao, Jiafeng Guo, Xueqi Cheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| place the markup on the true target (congruent) versus no markup (ablation) | Qwen3-VL-8B · Extremum Reasoning (counterfactual) | accuracy | Improved |
| place the markup on a distractor (incongruent) versus no markup (ablation) | Qwen3-VL-8B · Extremum Reasoning (counterfactual) | accuracy | Hurt |
| vary markup placement across seven variants (ablation) | Qwen3-VL-8B · Cell Retrieval (counterfactual) | accuracy: 94.5%-96.5% | No clear effect |
| use reference pipeline (docgraph, two-stage routing, DSL executor) instead of end-to-end MLLM | Reference pipeline vs Gemini 2.5 Flash · HighlightBench synthetic T4 | accuracy: 67.8 -> 81.5 | Improved |
| use reference pipeline instead of end-to-end MLLM | Reference pipeline vs Gemini 2.5 Flash · HighlightBench synthetic T3 | accuracy: 89.1 -> 73.3 | Hurt |
| use reference pipeline instead of end-to-end MLLM | Reference pipeline vs Gemini 2.5 Flash · HighlightBench real-world All | accuracy: 75.3 -> 77.1 | Improved |
| use reference pipeline instead of end-to-end MLLM | Reference pipeline vs Gemini 2.5 Flash · HighlightBench synthetic All | accuracy: 73.9 -> 72.3 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MiniCPM-V 4.5 — MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe (CVPR 2026) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding (CVPR 2025 · similarity 0.88)
- Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing (NeurIPS 2025 · similarity 0.86)
- Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling (CVPR 2026 · similarity 0.86)
- TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning (NeurIPS 2026 · similarity 0.86)
- TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning (ICLR 2026 · similarity 0.86)
- TableMix: Enhancing Multimodal Table Reasoning in MLLMs from a Data-Centric Perspective (CVPR 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
