Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Large vision-language models (LVLMs) excel across diverse tasks involving concrete images from natural scenes.However, their ability to interpret abstract figures, such as geometry shapes and scientific plots, remains limited due to a scarcity of training datasets in scientific domains.To fill this gap, we introduce Multimodal ArXiv, consisting of ArXivCap and ArXivQA, for enhancing LVLMs scientific comprehension.ArXivCap is a figure-caption dataset comprising 6.4M images and 3.9M captions, sourced from 572K ArXiv papers spanning various scientific domains.Drawing from ArXivCap, we introduce ArXivQA, a questionanswering dataset generated by prompting GPT-4V based on scientific figures.ArXivQA greatly enhances open-sourced LVLMs' mathematical reasoning capabilities, achieving a 10.4% absolute accuracy gain on a multimodal mathematical reasoning benchmark.Furthermore, employing ArXivCap, we devise four vision-to-text tasks for benchmarking LVLMs.Evaluation results with state-of-the-art LVLMs underscore their struggle with the nuanced semantics of academic figures, while domainspecific training yields substantial performance gains.Our error analysis uncovers misinterpretations of visual context, recognition errors, and the production of overly simplified captions by current LVLMs, shedding light on future improvements.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
Schuhmann, C., Vencu, R., Beaumont, R., Kaczmarczyk, R., Mullis, C., Katta, A., Coombes, T., Jitsev, J., & Komatsuzaki, A. (2021) · arXiv · doi:10.48550/arxiv.2111.02114 · Cited by 358
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
Lu, P., Bansal, H., Xia, T., Liu, J., Li, C., Hajishirzi, H., Cheng, H., Chang, K.-W., Galley, M., & Gao, J. (2023) · arXiv · doi:10.48550/arxiv.2310.02255 · Cited by 12
Cited by
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Fu, C., Dai, Y., Luo, Y., Li, L., Ren, S., Zhang, R., Wang, Z., Zhou, C., Shen, Y., Zhang, M., et al. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.02245 · Cited by 291
Self-citationFrom language to action: a review of large language models as autonomous agents and tool users
Chowa, S. S., Alvi, R., Rahman, S. S., Rahman, M. A., Raiaan, M. A. K., Islam, M. R., Hussain, M., & Azam, S. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-025-11471-9 · Cited by 50
M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models
Li, C., Shangguan, Z., Zhao, Y., Li, D., Liu, Y., & Cohan, A. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.904 · Cited by 8
Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
Ren, S., Xie, C., Jian, P., Ren, Z., Leng, C., & Zhang, J. (2025) · arXiv · doi:10.48550/arxiv.2503.24047 · Cited by 7
A Descriptive Review of Image Datasets for Accessible Alternative Descriptions in STEM Domains
Cardia, M., Buzzi, M., Galesi, G., & Leporini, B. (2025) · Proceedings of the 16th Biannual Conference of the Italian SIGCHI Chapter · doi:10.1145/3750069.3750122 · Cited by 5
Metadata
- Authors
- Li, L., Wang, Y., Xu, R., Wang, P., Feng, X., Kong, L., & Liu, Q.
- Venue
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 14369-14387
- OpenAlex
- W4402671151
- Cited by
- 36
- References
- 2
- FWCI
- 7.86
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models. https://app.cochat.ai/papers/10.18653/v1/2024.acl-long.775
- The paper
- Li, L., Wang, Y., Xu, R., Wang, P., Feng, X., Kong, L., & Liu, Q. (2024). Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/2024.acl-long.775
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.