XAI 陷入困境

IF 2.5 4区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Ai Magazine Pub Date : 2024-07-29 DOI:10.1002/aaai.12184
Rosina O Weber, Adam J Johs, Prateek Goel, João Marques Silva
{"title":"XAI 陷入困境","authors":"Rosina O Weber,&nbsp;Adam J Johs,&nbsp;Prateek Goel,&nbsp;João Marques Silva","doi":"10.1002/aaai.12184","DOIUrl":null,"url":null,"abstract":"<p>Researchers focusing on how artificial intelligence (AI) methods explain their decisions often discuss controversies and limitations. Some even assert that most publications offer little to no valuable contributions. In this article, we substantiate the claim that explainable AI (XAI) is in trouble by describing and illustrating four problems: the disagreements on the scope of XAI, the lack of definitional cohesion, precision, and adoption, the issues with motivations for XAI research, and limited and inconsistent evaluations. As we delve into their potential underlying sources, our analysis finds these problems seem to originate from AI researchers succumbing to the pitfalls of interdisciplinarity or from insufficient scientific rigor. Analyzing these potential factors, we discuss the literature at times coming across unexplored research questions. Hoping to alleviate existing problems, we make recommendations on precautions against the challenges of interdisciplinarity and propose directions in support of scientific rigor.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"45 3","pages":"300-316"},"PeriodicalIF":2.5000,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12184","citationCount":"0","resultStr":"{\"title\":\"XAI is in trouble\",\"authors\":\"Rosina O Weber,&nbsp;Adam J Johs,&nbsp;Prateek Goel,&nbsp;João Marques Silva\",\"doi\":\"10.1002/aaai.12184\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Researchers focusing on how artificial intelligence (AI) methods explain their decisions often discuss controversies and limitations. Some even assert that most publications offer little to no valuable contributions. In this article, we substantiate the claim that explainable AI (XAI) is in trouble by describing and illustrating four problems: the disagreements on the scope of XAI, the lack of definitional cohesion, precision, and adoption, the issues with motivations for XAI research, and limited and inconsistent evaluations. As we delve into their potential underlying sources, our analysis finds these problems seem to originate from AI researchers succumbing to the pitfalls of interdisciplinarity or from insufficient scientific rigor. Analyzing these potential factors, we discuss the literature at times coming across unexplored research questions. Hoping to alleviate existing problems, we make recommendations on precautions against the challenges of interdisciplinarity and propose directions in support of scientific rigor.</p>\",\"PeriodicalId\":7854,\"journal\":{\"name\":\"Ai Magazine\",\"volume\":\"45 3\",\"pages\":\"300-316\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2024-07-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12184\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ai Magazine\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/aaai.12184\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ai Magazine","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/aaai.12184","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

关注人工智能(AI)方法如何解释决策的研究人员经常讨论争议和局限性。有些人甚至断言,大多数出版物几乎没有任何有价值的贡献。在这篇文章中,我们通过描述和说明四个问题来证实 "可解释人工智能(XAI)陷入困境 "的说法:对 XAI 范围的分歧,定义缺乏一致性、精确性和采用性,XAI 研究的动机问题,以及有限且不一致的评估。当我们深入探究这些问题的潜在根源时,我们的分析发现,这些问题似乎都源于人工智能研究人员屈从于跨学科的陷阱或科学严谨性不足。通过分析这些潜在因素,我们讨论了文献中时常出现的未探索的研究问题。为了缓解现有问题,我们提出了防范跨学科挑战的建议,并提出了支持科学严谨性的方向。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

XAI is in trouble

XAI is in trouble

Researchers focusing on how artificial intelligence (AI) methods explain their decisions often discuss controversies and limitations. Some even assert that most publications offer little to no valuable contributions. In this article, we substantiate the claim that explainable AI (XAI) is in trouble by describing and illustrating four problems: the disagreements on the scope of XAI, the lack of definitional cohesion, precision, and adoption, the issues with motivations for XAI research, and limited and inconsistent evaluations. As we delve into their potential underlying sources, our analysis finds these problems seem to originate from AI researchers succumbing to the pitfalls of interdisciplinarity or from insufficient scientific rigor. Analyzing these potential factors, we discuss the literature at times coming across unexplored research questions. Hoping to alleviate existing problems, we make recommendations on precautions against the challenges of interdisciplinarity and propose directions in support of scientific rigor.

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
Ai Magazine
Ai Magazine 工程技术-计算机:人工智能
CiteScore
3.90
自引率
11.10%
发文量
61
审稿时长
>12 weeks
期刊介绍: AI Magazine publishes original articles that are reasonably self-contained and aimed at a broad spectrum of the AI community. Technical content should be kept to a minimum. In general, the magazine does not publish articles that have been published elsewhere in whole or in part. The magazine welcomes the contribution of articles on the theory and practice of AI as well as general survey articles, tutorial articles on timely topics, conference or symposia or workshop reports, and timely columns on topics of interest to AI scientists.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信