以用户为中心的可解释人工智能:设计和评估一种方法,为结构化数据生成连贯的反事实解释

IF 2.8 Q2 OPERATIONS RESEARCH & MANAGEMENT SCIENCE Journal of Decision Systems Pub Date : 2022-09-06 DOI:10.1080/12460125.2022.2119707
Maximilian Förster, Philipp Hühn, Mathias Klier, Kilian Kluge
{"title":"以用户为中心的可解释人工智能:设计和评估一种方法,为结构化数据生成连贯的反事实解释","authors":"Maximilian Förster, Philipp Hühn, Mathias Klier, Kilian Kluge","doi":"10.1080/12460125.2022.2119707","DOIUrl":null,"url":null,"abstract":"ABSTRACT Many Artificial Intelligence (AI) systems are black boxes, which hinders their deployment. Explainable AI (XAI) approaches which automatically generate counterfactual explanations aim to assist users in scrutinising AI decisions. One property of explanations crucial for their acceptance by users is their coherence. Users perceive counterfactual explanations as coherent if they present a realistic/typical counterfactual scenario that is suitable to explain the factual situation. We design an optimisation-based approach to generate coherent counterfactual explanations applicable to structured data. We demonstrate its applicability and rigorously evaluate its efficacy through functionally grounded and human-grounded evaluation. Results suggest that our approach indeed produces counterfactual explanations that are perceived as coherent by users. More specifically, they are perceived as more realistic, typical, and feasible than state-of-the-art explanations.","PeriodicalId":45565,"journal":{"name":"Journal of Decision Systems","volume":" ","pages":""},"PeriodicalIF":2.8000,"publicationDate":"2022-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"User-centric explainable AI: design and evaluation of an approach to generate coherent counterfactual explanations for structured data\",\"authors\":\"Maximilian Förster, Philipp Hühn, Mathias Klier, Kilian Kluge\",\"doi\":\"10.1080/12460125.2022.2119707\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ABSTRACT Many Artificial Intelligence (AI) systems are black boxes, which hinders their deployment. Explainable AI (XAI) approaches which automatically generate counterfactual explanations aim to assist users in scrutinising AI decisions. One property of explanations crucial for their acceptance by users is their coherence. Users perceive counterfactual explanations as coherent if they present a realistic/typical counterfactual scenario that is suitable to explain the factual situation. We design an optimisation-based approach to generate coherent counterfactual explanations applicable to structured data. We demonstrate its applicability and rigorously evaluate its efficacy through functionally grounded and human-grounded evaluation. Results suggest that our approach indeed produces counterfactual explanations that are perceived as coherent by users. More specifically, they are perceived as more realistic, typical, and feasible than state-of-the-art explanations.\",\"PeriodicalId\":45565,\"journal\":{\"name\":\"Journal of Decision Systems\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2022-09-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Decision Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1080/12460125.2022.2119707\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"OPERATIONS RESEARCH & MANAGEMENT SCIENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Decision Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/12460125.2022.2119707","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OPERATIONS RESEARCH & MANAGEMENT SCIENCE","Score":null,"Total":0}
引用次数: 2
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
User-centric explainable AI: design and evaluation of an approach to generate coherent counterfactual explanations for structured data
ABSTRACT Many Artificial Intelligence (AI) systems are black boxes, which hinders their deployment. Explainable AI (XAI) approaches which automatically generate counterfactual explanations aim to assist users in scrutinising AI decisions. One property of explanations crucial for their acceptance by users is their coherence. Users perceive counterfactual explanations as coherent if they present a realistic/typical counterfactual scenario that is suitable to explain the factual situation. We design an optimisation-based approach to generate coherent counterfactual explanations applicable to structured data. We demonstrate its applicability and rigorously evaluate its efficacy through functionally grounded and human-grounded evaluation. Results suggest that our approach indeed produces counterfactual explanations that are perceived as coherent by users. More specifically, they are perceived as more realistic, typical, and feasible than state-of-the-art explanations.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Decision Systems
Journal of Decision Systems OPERATIONS RESEARCH & MANAGEMENT SCIENCE-
CiteScore
6.30
自引率
23.50%
发文量
55
期刊最新文献
Public acceptance of smart home technologies in the UK: a citizens’ jury study Perceptions of facilitators towards adoption of AI-based solutions for sustainable agriculture I am therefore, I do: a fit perspective of decision-making styles and business intelligence usage AI: A knowledge sharing tool for improving employees’ performance Data-driven decision making in advanced manufacturing Systems: modeling and analysis of critical success factors
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1