Salvato in:
Dettagli Bibliografici
Autori principali: Yin, Xiaoyun, Doost, Elmira Zahmat, Zhou, Shiwen, Yadav, Garima Arya, Gorman, Jamie C.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.02660
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912625698275328
author Yin, Xiaoyun
Doost, Elmira Zahmat
Zhou, Shiwen
Yadav, Garima Arya
Gorman, Jamie C.
author_facet Yin, Xiaoyun
Doost, Elmira Zahmat
Zhou, Shiwen
Yadav, Garima Arya
Gorman, Jamie C.
contents When researchers claim AI systems possess ToM or mental models, they are fundamentally discussing behavioral predictions and bias corrections rather than genuine mental states. This position paper argues that the current discourse conflates sophisticated pattern matching with authentic cognition, missing a crucial distinction between simulation and experience. While recent studies show LLMs achieving human-level performance on ToM laboratory tasks, these results are based only on behavioral mimicry. More importantly, the entire testing paradigm may be flawed in applying individual human cognitive tests to AI systems, but assessing human cognition directly in the moment of human-AI interaction. I suggest shifting focus toward mutual ToM frameworks that acknowledge the simultaneous contributions of human cognition and AI algorithms, emphasizing the interaction dynamics, instead of testing AI in isolation.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02660
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?
Yin, Xiaoyun
Doost, Elmira Zahmat
Zhou, Shiwen
Yadav, Garima Arya
Gorman, Jamie C.
Human-Computer Interaction
Artificial Intelligence
When researchers claim AI systems possess ToM or mental models, they are fundamentally discussing behavioral predictions and bias corrections rather than genuine mental states. This position paper argues that the current discourse conflates sophisticated pattern matching with authentic cognition, missing a crucial distinction between simulation and experience. While recent studies show LLMs achieving human-level performance on ToM laboratory tasks, these results are based only on behavioral mimicry. More importantly, the entire testing paradigm may be flawed in applying individual human cognitive tests to AI systems, but assessing human cognition directly in the moment of human-AI interaction. I suggest shifting focus toward mutual ToM frameworks that acknowledge the simultaneous contributions of human cognition and AI algorithms, emphasizing the interaction dynamics, instead of testing AI in isolation.
title When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2510.02660