Artificial Intelligence and the Illusion of Understanding: A Systematic Review of Theory of Mind and Large Language Models

幻觉 认知科学 心理学 认识论 认知心理学 哲学
作者
Antonella Marchetti,Federico Manzi,Giuseppe Riva,Andrea Gaggioli,Davide Massaro
出处
期刊:Cyberpsychology, Behavior, and Social Networking [Mary Ann Liebert, Inc.]
卷期号:28 (7): 505-514 被引量:19
标识
DOI:10.1089/cyber.2024.0536
摘要

The development of Large Language Models (LLMs) has sparked significant debate regarding their capacity for Theory of Mind (ToM)-the ability to attribute mental states to oneself and others. This systematic review examines the extent to which LLMs exhibit Artificial ToM (AToM) by evaluating their performance on ToM tasks and comparing it with human responses. While LLMs, particularly GPT-4, perform well on first-order false belief tasks, they struggle with more complex reasoning, such as second-order beliefs and recursive inferences, where humans consistently outperform them. Moreover, the review underscores the variability in ToM assessments, as many studies adapt classical tasks for LLMs, raising concerns about comparability with human ToM. Most evaluations remain constrained to text-based tasks, overlooking embodied and multimodal dimensions crucial to human social cognition. This review discusses the "illusion of understanding" in LLMs for two primary reasons: First, their lack of the developmental and cognitive mechanisms necessary for genuine ToM, and second, methodological biases in test designs that favor LLMs' strengths, limiting direct comparisons with human performance. The findings highlight the need for more ecologically valid assessments and interdisciplinary research to better delineate the limitations and potential of AToM. This set of issues is highly relevant to psychology, as language is generally considered just one component in the broader development of human ToM, a perspective that contrasts with the dominant approach in AToM studies. This discrepancy raises critical questions about the extent to which human ToM and AToM are comparable.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
不想做科研的不是好牛马完成签到,获得积分20
1秒前
曾靖玮发布了新的文献求助10
2秒前
重阳糕发布了新的文献求助10
2秒前
苏木发布了新的文献求助10
2秒前
3秒前
Hello的应助被xiaohu6311采纳,获得10
3秒前
Skywalker发布了新的文献求助10
4秒前
4秒前
棉花糖发布了新的文献求助10
5秒前
冷静的访天完成签到,获得积分10
5秒前
6秒前
6秒前
jiangjiang完成签到,获得积分10
8秒前
9秒前
stackheap完成签到,获得积分10
10秒前
11111发布了新的文献求助10
11秒前
11秒前
何时是归宿完成签到 ,获得积分10
12秒前
YZZ完成签到,获得积分10
12秒前
谦让盼山完成签到,获得积分10
12秒前
低贱牛马完成签到 ,获得积分10
13秒前
王蕊完成签到 ,获得积分10
13秒前
所所的应助被yanr采纳,获得10
13秒前
端庄的千凡完成签到,获得积分10
13秒前
14秒前
余叶完成签到 ,获得积分10
14秒前
lin完成签到,获得积分10
15秒前
余香的应助被morena采纳,获得10
15秒前
FashionBoy的应助被田园南拳皇采纳,获得10
16秒前
16秒前
16秒前
16秒前
anchoro完成签到,获得积分10
17秒前
xiaohu6311完成签到,获得积分10
19秒前
19秒前
19秒前
英俊鼠标完成签到 ,获得积分10
20秒前
20秒前
CipherSage的应助被syy采纳,获得10
21秒前
ZZShuang发布了新的文献求助10
21秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
What Else Can I Tell You?: A Pragmatic Study of English Rhetorical Questions as Discursive and Argumentative Acts 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8158017
求助须知:如何正确求助?哪些是违规求助? 9553900
关于积分的说明 21716555
捐赠科研通 7747340
什么是DOI,文献DOI怎么找? 3426934
关于科研通互助平台的介绍 2551639
邀请新用户注册赠送积分活动 2471005