Metraipolis › archive › dc_e46ee38b2b1e
SciDiagBench: A Type-Specific Benchmark for Human-Aligned Evaluation of Scientific Diagrams — arXiv:2610.27841
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.27841
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:09:02.803Z
- SHA-256 of the archived text
c1ddb5e6b93969802a70e8917bb0fbb1a22371618912af0cffc703c234d991e7- Stable URL of this page
https://metraipolis.com/documento/dc_e46ee38b2b1e
How to cite
SciDiagBench: A Type-Specific Benchmark for Human-Aligned Evaluation of Scientific Diagrams — arXiv:2610.27841 — arXiv (en), https://arxiv.org/abs/2610.27841 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e46ee38b2b1e (Metraipolis archive dc_e46ee38b2b1e, sha256 c1ddb5e6b93969802a70e8917bb0fbb1a22371618912af0cffc703c234d991e7)
BibTeX
@misc{dce46ee38b2b1e,
title = {SciDiagBench: A Type-Specific Benchmark for Human-Aligned Evaluation of Scientific Diagrams — arXiv:2610.27841},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.27841},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e46ee38b2b1e; sha256 c1ddb5e6b93969802a70e8917bb0fbb1a22371618912af0cffc703c234d991e7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27841. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent agents have demonstrated strong capabilities in generating images from textual prompts, motivating their utilization for scientific diagram generation. Scientific diagrams naturally span diverse types, each characterized by distinct visual structures and content organization. Consequently, during peer review and other scientific evaluation, human experts naturally consider type-specific criteria when assessing their quality. However, existing VLM-based evaluation benchmarks fail to reflect the above human evaluation practices for two main reasons: 1) benchmark datasets typically lack a systematic categorization of different diagram types and thus adopt the same generic criteria for all diagrams, and 2) their evaluation criteria are often designed heuristically, without explicit alignment to human evaluation preferences. Motivated by these limitations, we introduce SciDiagBench, which consists of a benchmark dataset that systematically categorizes scientific diagrams into 11 types and a human preference-guided evaluation method. Specifically, SciDiagBench contains 165 scientific diagrams across 10 broad domains, with types including graphical abstracts, technical roadmaps, and illustrative cases. Based on this dataset, SciDiagBench develops an evaluation method that leverages a preference-guided calibration process to incorporate human preferences into the generation of type-specific criteria. Ultimately, SciDiagBench enables more reliable automated evaluation that better aligns with human evaluation across diverse scientific diagrams. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.27841 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-21T07:05:58.132Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).