评估可解释性的需求工程实践：将戴姆勒卡车公司的见解整合到一个可解释的需求工程框架提案中
Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal
查看机构详情
- TUM School of CIT, Technical University of Munich（慕尼黑技术大学 CIT 学院）
- Institute of Software Engineering, University of Stuttgart（斯图加特大学软件工程研究所）
- Department of Computer Science, Vrije Universiteit Amsterdam（阿姆斯特丹自由大学计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
研究现有需求工程实践对可解释性要求的支持，通过对戴姆勒卡车公司从业者的多阶段定性研究，揭示各步骤挑战，表明当前实践支持有限，为开发可解释人工智能的需求工程框架提供实证见解与研究愿景。
中文摘要 AI 辅助
可解释性已成为基于人工智能的系统的关键要求，特别是在安全关键和受监管的领域。尽管先前的研究已经提出了框架、模式和以用户为中心的方法来支持可解释性，但对于现有需求工程（RE）实践如何在整个RE生命周期中支持可解释性要求，特别是在工业环境中，实证理解有限。本文报告了一项正在进行的基于行业的研究的早期发现，该研究调查了如何使用既定的RE技术来引出、指定和验证可解释性要求。我们对戴姆勒卡车公司的八位从业者进行了多阶段定性研究，在需求引出、规范和验证步骤中采用了出声思考协议和主持小组讨论。我们的初步分析揭示了所有步骤中反复出现的挑战，包括引出过程中的概念模糊性、规范过程中的可测试性和表达性有限，以及由于标准模糊和监管不确定性导致的验证碎片化。这些发现表明，当前的RE实践在系统地解决可解释性要求方面提供的支持有限。本文贡献了针对特定步骤和交叉挑战的实证见解，并概述了朝着为基于可解释人工智能的系统开发基于实证的RE框架的研究愿景。
英文摘要
Explainability has emerged as a critical requirement for AI-based systems, particularly in safety-critical and regulated domains. Although prior research has proposed frameworks, patterns, and user-centered approaches to support explainability, there is limited empirical understanding of how existing Requirements Engineering (RE) practices support explainability requirements across the RE lifecycle, especially in an industrial context. This paper reports early findings from an ongoing industry-based study investigating how explainability requirements are elicited, specified, and validated using established RE techniques. We conducted a multi-phase qualitative study with eight practitioners at Daimler Truck, employing think-aloud protocols and moderated group discussions across requirements elicitation, specification, and validation steps. Our preliminary analysis reveals recurring challenges across all steps, including conceptual ambiguity during elicitation, limited testability and expressiveness during specification, and fragmented validation due to vague criteria and regulatory uncertainty. These findings indicate that current RE practices provide limited support to systematically address explainability requirements. The paper contributes empirical insights into step-specific and cross-cutting challenges and outlines a research vision toward developing an empirically grounded RE framework for explainable AI-based systems.
