arXiv cs.AI· Ruchira Dhar, Danae Sanchez Villegas, Antonia Karamolegkou, Alice Schiavone, Yifei Yuan, Xinyi Chen, Jiaang Li, Stella Frank, Laura De Grazia, Monorama Swain, Stephanie Brandl, Daniel Hershcovich, Anders S{\o}gaard, Desmond Elliott·· 3 小时前AI 评分36
EvalCards：标准化评估报告框架
EvalCards: A Framework for Standardized Evaluation Reporting
AI 导读
一项来自 arXiv 的研究提出 EvalCards 框架，用于规范通用 AI（GPAI）模型的评估报告。作者梳理现有评估报告实践后，归纳出可复现性、可访问性和可问责性三大核心问题，并给出简明评估摘要的初步格式。该框架可用于指导未来评估报告标准的制定。
正文 · 原文
Authors:Ruchira Dhar, Danae Sanchez Villegas, Antonia Karamolegkou, Alice Schiavone, Yifei Yuan, Xinyi Chen, Jiaang Li, Stella Frank, Laura De Grazia, Monorama Swain, Stephanie Brandl, Daniel Hershcovich, Anders Søgaard, Desmond Elliott
Abstract:Evaluation reports guide the use of general-purpose AI (GPAI) models, yet inconsistent reporting often leaves essential questions unanswered. Through a review of prior work, we identify three central issues in evaluation reporting practices today, reproducibility, accessibility, and accountability, and examine how existing reporting artifacts fall short in addressing them. We introduce the EvalCards framework, outlining its key dimensions and presenting a preliminary format for concise evaluation summaries. We conclude by discussing how the framework can guide the future development of evaluation reporting standards.
| Comments: | Version 2: Updated review details, figures, and specifics of GPAI case studies |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY) |
| Cite as: | arXiv:2511.21695 [cs.CL] |
| (or arXiv:2511.21695v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2511.21695 arXiv-issued DOI via DataCite |
Submission history
From: Ruchira Dhar [view email]
[v1]
Wed, 5 Nov 2025 19:01:48 UTC (159 KB)
[v2]
Fri, 23 Oct 2026 13:35:53 UTC (174 KB)
来源：arXiv cs.AI · arxiv.org