flâneur

[2506.13403] Deflating Deflationism: A Critical Perspective on Debunking Arguments Against LLM Mentality

arxiv.org · 8,610 words · saved by 1 readers

Abstract:Many people feel compelled to interpret, describe, and respond to Large Language Models (LLMs) as if they possess inner mental lives similar to our own. Responses to this phenomenon have varied. Inflationists hold that at least some folk psychological ascriptions to LLMs are warranted. Deflationists argue that all such attributions of mentality to LLMs are misplaced, often cautioning against the risk that anthropomorphic projection may lead to misplaced trust or potentially even confusion about the moral status of LLMs. We advance this debate by assessing two common deflationary arguments against LLM mentality. What we term the 'robustness strategy' aims to undercut one justification for believing that LLMs are minded entities by showing that putatively cognitive and humanlike behaviours are not robust, failing to generalise appropriately. What we term the 'etiological strategy' undercuts attributions of mentality by challenging naive causal explanations of LLM behaviours, offering alternative causal accounts that weaken the case for mental state attributions. While both strategies offer powerful challenges to full-blown inflationism, we find that neither strategy provides a knock-down case against ascriptions of mentality to LLMs simpliciter. With this in mind, we explore a modest form of inflationism that permits ascriptions of mentality to LLMs under certain conditions. Specifically, we argue that folk practice provides a defeasible basis for attributing mental states and capacities to LLMs provided those mental states and capacities can be understood in metaphysically undemanding terms (e.g. knowledge, beliefs and desires), while greater caution is required when attributing metaphysically demanding mental phenomena such as phenomenal consciousness.

Deflating Deflationism: A Critical Perspective on Debunking Arguments Against LLM Mentality Alex Grzankowski1,* , Geoff Keeling2,* , Henry Shevlin3,* , and Winnie Street2,* arXiv:2506.13403v1 [cs.AI] 16 Jun 2025 1 Institute of Philosophy, University of London 2 Google, Paradigms of Intelligence Team…

related reading