Conference paper · 2025 · Open access

SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers

Zihang Wang, Yilun Zhao, Kaiyan Zhang, Chenguang Zhao, Manasi S. Patwardhan, Arman Cohan

Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP), 403–417 · Published 1 January 2025 · DOI 10.18653/v1/2025.emnlp-demos.28

Free PDFView at the publisherCite this paper

In brief

“SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers” is a 2025 conference paper by Zihang Wang and 5 co-authors, published in Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP). OpenAlex counts 1 citations as of 15 November 2026, which puts it in the top 9% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP).

Citations
1
Most cited in
2026 (1)
Field-weighted impact
2.98
References
3
Authors
6

Abstract

High-quality schematic diagrams, which provide a conceptual overview of the research, play a crucial role in summarizing and clarifying a study's core ideas.However, creating these diagrams is time-consuming for authors and remains challenging for current AI systems, as it requires both a deep understanding of the paper's content and a strong sense of visual design.To address this, we introduce SCISKETCH, an open-source framework that supports two automated workflows for schematic diagram generation using foundation models, shown in Figure 1. 1) In the graphiccode-based workflow, SCISKETCH follows a two-stage pipeline: it first produces a layout plan expressed in a graphical code language with a self-refinement and self-verification mechanism.It then integrates empirical images and symbolic icons to create a visually coherent, informative diagram.2) In the image-based workflow, SCISKETCH directly synthesizes the diagram image through image generation with a self-refinement mechanism.Through both automatic and human evaluations, we show that SCISKETCH outperforms several state-ofthe-art foundation models, including GPT-4o, Claude-3.7-Sonnetand Gemini-2.5-Pro, in generating schematic diagrams for scientific papers.We make SCISKETCH fully open-sourced, providing researchers with an accessible, extensible tool for high-quality schematic diagram generation in scientific fields.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wang, Z., Zhao, Y., Zhang, K., Zhao, C., Patwardhan, M. S., & Cohan, A. (2025). SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers. Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP), 403–417. https://doi.org/10.18653/v1/2025.emnlp-demos.28

MLA 9

Wang, Zihang, et al. “SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers.” Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP), 2025, pp. 403–417. https://doi.org/10.18653/v1/2025.emnlp-demos.28.

Chicago

Wang, Zihang, Yilun Zhao, Kaiyan Zhang, Chenguang Zhao, Manasi S. Patwardhan, and Arman Cohan. 2025. “SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers.” Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP): 403–417. https://doi.org/10.18653/v1/2025.emnlp-demos.28.

Harvard

Wang, Z. et al. (2025) ‘SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers’, Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP), pp. 403–417. doi:10.18653/v1/2025.emnlp-demos.28.

IEEE

Z. Wang, Y. Zhao, K. Zhang, C. Zhao, M. S. Patwardhan, and A. Cohan, “SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers,” Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP), pp. 403–417, 2025, doi: 10.18653/v1/2025.emnlp-demos.28.

BibTeX

@inproceedings{wang2025scisketch,
  title     = {{SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers}},
  author    = {Wang, Zihang and Zhao, Yilun and Zhang, Kaiyan and Zhao, Chenguang and Patwardhan, Manasi S. and Cohan, Arman},
  booktitle = {Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)},
  year      = {2025},
  pages     = {403--417},
  doi       = {10.18653/v1/2025.emnlp-demos.28},
  url       = {https://doi.org/10.18653/v1/2025.emnlp-demos.28}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Social Sciences › Social Sciences › Library and Information Sciences › Academic Writing and Publishing

  • scientific publications
  • automated diagram generation
  • graphic codes
  • layout planning
  • foundation models
  • self-refinement
  • visual design
  • scientific visualization

Work with this paper

Most-cited papers in Social Sciences

All highly cited Social Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Wang, Z., Zhao, Y., Zhang, K., Zhao, C., Patwardhan, M. S., & Cohan, A. (2025). SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers. Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP), 403–417. https://doi.org/10.18653/v1/2025.emnlp-demos.28

How many times has this paper been cited?

1 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP).

Who wrote this paper?

Zihang Wang, Yilun Zhao, Kaiyan Zhang, Chenguang Zhao, Manasi S. Patwardhan, Arman Cohan.

What is the DOI of this paper?

10.18653/v1/2025.emnlp-demos.28. The permanent link is https://doi.org/10.18653/v1/2025.emnlp-demos.28.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.