Loopholes: A window into value alignment and the communication of meaning

IF 2.8 1区 心理学 Q1 PSYCHOLOGY, EXPERIMENTAL
Sophie Bridgers , Peng Qian , Kiera Parece , Maya Taliaferro , Laura Schulz , Tomer D. Ullman
{"title":"Loopholes: A window into value alignment and the communication of meaning","authors":"Sophie Bridgers ,&nbsp;Peng Qian ,&nbsp;Kiera Parece ,&nbsp;Maya Taliaferro ,&nbsp;Laura Schulz ,&nbsp;Tomer D. Ullman","doi":"10.1016/j.cognition.2025.106131","DOIUrl":null,"url":null,"abstract":"<div><div>Intentional misunderstandings take advantage of the ambiguity of language to do what someone said, instead of what they actually wanted. These purposeful misconstruals or <em>loopholes</em> are a familiar facet of fable, law, and everyday life. Engaging with loopholes requires a nuanced understanding of goals (your own and those of others), ambiguity, and social alignment. As such, loopholes provide a unique window into the normal operations of cooperation and communication. Despite their pervasiveness and utility in social interaction, research on loophole behavior is scarce. Here, we combine a theoretical analysis with empirical data to give a framework of loophole behavior. We first establish that loopholes are widespread, and exploited most often in equal or subordinate relationships (Study 1). We show that people reliably distinguish loophole behavior from both compliance and non-compliance (Study 2), and that people predict that others are most likely to exploit loopholes when their goals are in conflict with their social partner’s and there is a cost for non-compliance (Study 3). We discuss these findings in light of other computational frameworks for communication and joint-planning, as well as discuss how loophole behavior might develop and the implications of this work for human–machine alignment.</div></div>","PeriodicalId":48455,"journal":{"name":"Cognition","volume":"261 ","pages":"Article 106131"},"PeriodicalIF":2.8000,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cognition","FirstCategoryId":"102","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S001002772500071X","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHOLOGY, EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0

Abstract

Intentional misunderstandings take advantage of the ambiguity of language to do what someone said, instead of what they actually wanted. These purposeful misconstruals or loopholes are a familiar facet of fable, law, and everyday life. Engaging with loopholes requires a nuanced understanding of goals (your own and those of others), ambiguity, and social alignment. As such, loopholes provide a unique window into the normal operations of cooperation and communication. Despite their pervasiveness and utility in social interaction, research on loophole behavior is scarce. Here, we combine a theoretical analysis with empirical data to give a framework of loophole behavior. We first establish that loopholes are widespread, and exploited most often in equal or subordinate relationships (Study 1). We show that people reliably distinguish loophole behavior from both compliance and non-compliance (Study 2), and that people predict that others are most likely to exploit loopholes when their goals are in conflict with their social partner’s and there is a cost for non-compliance (Study 3). We discuss these findings in light of other computational frameworks for communication and joint-planning, as well as discuss how loophole behavior might develop and the implications of this work for human–machine alignment.
漏洞:价值对齐和意义沟通的窗口
故意误解利用语言的模糊性去做别人说的,而不是他们真正想要的。这些有目的的误解或漏洞是寓言、法律和日常生活中常见的一面。利用漏洞需要对目标(自己和他人的目标)、模糊性和社会一致性有细致入微的理解。因此,漏洞为合作与沟通的正常运作提供了一个独特的窗口。尽管漏洞行为在社会交往中普遍存在并发挥着重要作用,但对漏洞行为的研究却很少。本文将理论分析与实证数据相结合,给出了漏洞行为的框架。我们首先确立了漏洞是普遍存在的,并且最常在平等或从属关系中被利用(研究1)。我们表明,人们可靠地将漏洞行为与合规和不合规区分开来(研究2)。人们预测,当他人的目标与他们的社会伙伴的目标相冲突时,他们最有可能利用漏洞,并且有不遵守的成本(研究3)。我们根据其他通信和联合规划的计算框架讨论了这些发现,并讨论了漏洞行为如何发展以及这项工作对人机校准的影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Cognition
Cognition PSYCHOLOGY, EXPERIMENTAL-
CiteScore
6.40
自引率
5.90%
发文量
283
期刊介绍: Cognition is an international journal that publishes theoretical and experimental papers on the study of the mind. It covers a wide variety of subjects concerning all the different aspects of cognition, ranging from biological and experimental studies to formal analysis. Contributions from the fields of psychology, neuroscience, linguistics, computer science, mathematics, ethology and philosophy are welcome in this journal provided that they have some bearing on the functioning of the mind. In addition, the journal serves as a forum for discussion of social and political aspects of cognitive science.
×
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