# SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning

arXiv: https://arxiv.org/abs/2511.15090 · HTML: https://mlsanity.com/paper/2511.15090/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 19 Nov 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 7 of 7)

- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Thyme: Think Beyond Images](https://mlsanity.com/paper/2508.11630/) (2025)
- [Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models](https://mlsanity.com/paper/2403.00231/) (2024)
- [DeepEyesV2: Toward Agentic Multimodal Model](https://mlsanity.com/paper/2511.05271/) (2025)
- [BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations](https://mlsanity.com/paper/2501.03403/) (2025)

## Built on by (most cited first, 4 of 4)

- [DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding](https://mlsanity.com/paper/2605.08888/) (2026)
- [Hierarchical Evidence-Driven Reasoning for Long Document Understanding](https://mlsanity.com/paper/2607.04625/) (2026)
- [Spatially-Grounded Document Retrieval via Patch-to-Region Relevance Propagation](https://mlsanity.com/paper/2512.02660/) (2025)
- [HighlightBench: Benchmarking Markup-Driven Table Reasoning in Scientific Documents](https://mlsanity.com/paper/2603.26784/) (2026)

## Abstract (arXiv)

Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at the page level without explicitly annotating the evidence regions that support the answer, which limits both interpretability and the reliability of evaluation. To address this limitation, we introduce SciEGQA, a scientific document question answering and reasoning dataset with semantic evidence grounding, where supporting evidence is represented as semantically coherent document regions annotated with bounding boxes. SciEGQA consists of two components: a **human-annotated fine-grained benchmark** containing 1,623 high-quality question--answer pairs, and a **large-scale automatically constructed training set** with over 30K QA pairs generated through an automated data construction pipeline. Extensive experiments on a wide range of Vision-Language Models (VLMs) show that existing models still struggle with evidence localization and evidence-based question answering in scientific documents. Training on the proposed dataset significantly improves the scientific reasoning capabilities of VLMs. The project page is available at https://yuwenhan07.github.io/SciEGQA-project/.