arXiv cs.AI· Zihan Deng, Chuanzhi Xu, Huiqi Liang, Xiaozhen Zhong, Weidong Cai, Lequan Yu·· 10 小时前AI 评分27
SciFigQual-Bench:结合稿件上下文的科学图表质量评估基准
SciFigQual-Bench: Scientific Figure Quality Assessment with Manuscript-Linked Context
AI 导读
研究者提出 SciFigQual-Bench,一个面向已发表计算机会议论文图表的稿件关联基准,将每张图与其标题及索引解析出的引用段落绑定,从视觉清晰度、布局、标题一致性、上下文一致性和误导风险五个维度评分,证据缺失时该维度留空不评。
正文 · 原文
Abstract:Scientific figure quality is bound to the manuscript: a crop can be visually clear and still contradict its caption or the paragraph that cites it. Most image quality assessment and chart-understanding methods target a detached visual surface or a question-answering score, rather than alignment among the figure, its caption, and the citing text. A single end-to-end prompt that sees the image and the text together still mixes what is visible with what the caption and the citing paragraph claim, so fluent wording can raise a visual score and missing text can be treated as low quality. To address this gap, we introduce SciFigQual-Bench, a manuscript-linked benchmark for published CS-conference figures that binds each figure to its caption and to index-resolved citing paragraphs, and scores visual clarity, layout, caption consistency, context consistency, and misleading risk, leaving a dimension unevaluated when its evidence is absent. SFQ-Agent reads the image and the text in separate calls and records modality-specific evidence. A cross-modal judge scores caption and citing-text alignment from those reports, and a deterministic runner keeps the visual scores, sets misleading risk by a fixed rule, and applies the written caps, so each dimension follows the rubric instead of a single end-to-end prompt. Experiments comparing this staged judge with single-pass and OCR-sidecar protocols find the closest point-estimate fit to mean human ratings under staged judging, while the gap between protocols remains small. Caption consistency remains the main gap, and agreement with the rater mean answers a different question from agreement among human raters. Project page: this https URL
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.6; I.2.10; I.4.8 |
| Cite as: | arXiv:2607.27084 [cs.CV] |
| (or arXiv:2607.27084v4 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.27084 arXiv-issued DOI via DataCite |
Submission history
From: Zihan Deng [view email]
[v1]
Wed, 29 Jul 2026 16:07:44 UTC (4,068 KB)
[v2]
Thu, 10 Sep 2026 15:49:22 UTC (3,840 KB)
[v3]
Sat, 26 Sep 2026 17:02:21 UTC (4,820 KB)
[v4]
Wed, 18 Nov 2026 08:57:18 UTC (4,397 KB)
来源:arXiv cs.AI · arxiv.org