What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks

Author:

Sokol Kacper1ORCID,Vogt Julia E.1ORCID

Affiliation:

1. Department of Computer Science, ETH Zurich, Switzerland

Funder

Hasler Stiftung

Publisher

ACM

Reference85 articles.

1. Peter Achinstein. 1983. The nature of explanation. Oxford University Press on Demand.

2. Mark S. Ackerman. 2000. The intellectual challenge of CSCW: The gap between social requirements and technical feasibility. Human–Computer Interaction 15, 2-3 (2000), 179–203.

3. OpenXAI: Towards a transparent evaluation of model explanations;Agarwal Chirag;Advances in Neural Information Processing Systems,2022

4. David Alvarez-Melis and Tommi S Jaakkola. 2018. On the robustness of interpretability methods. 3rd Workshop on Human Interpretability in Machine Learning (WHI 2018) at the 35th International Conference on Machine Learning (ICML 2018), Stockholm, Sweden (2018). arXiv:1806.08049

5. Kasun Amarasinghe Kit T Rodolfa Sérgio Jesus Valerie Chen Vladimir Balayan Pedro Saleiro Pedro Bizarro Ameet Talwalkar and Rayid Ghani. 2022. On the importance of application-grounded experimental design for evaluating explainable machine learning methods. (2022). arXiv:2206.13503

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Interpretable representations in explainable AI: from theory to practice;Data Mining and Knowledge Discovery;2024-04-25

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3