AI Paper Atlas

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

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
place the markup on the true target (congruent) versus no markup (ablation)Qwen3-VL-8B · Extremum Reasoning (counterfactual)accuracyImproved
place the markup on a distractor (incongruent) versus no markup (ablation)Qwen3-VL-8B · Extremum Reasoning (counterfactual)accuracyHurt
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 MLLMReference pipeline vs Gemini 2.5 Flash · HighlightBench synthetic T4accuracy: 67.8 -> 81.5Improved
use reference pipeline instead of end-to-end MLLMReference pipeline vs Gemini 2.5 Flash · HighlightBench synthetic T3accuracy: 89.1 -> 73.3Hurt
use reference pipeline instead of end-to-end MLLMReference pipeline vs Gemini 2.5 Flash · HighlightBench real-world Allaccuracy: 75.3 -> 77.1Improved
use reference pipeline instead of end-to-end MLLMReference pipeline vs Gemini 2.5 Flash · HighlightBench synthetic Allaccuracy: 73.9 -> 72.3Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy