[2603.28925] Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs

Computer Science > Computation and Language arXiv:2603.28925 (cs) [Submitted on 30 Mar 2026] Title:Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs Authors:Junsol Kim, Winnie Street, Roberta Rocca, Daine M. Korngiebel, Adam Waytz, James Evans, Geoff Keeling View a PDF of the paper titled Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs, by Junsol Kim and 6 other authors View PDF HTML (experimental) Abstract:Safety fine-tuning in Large Language Models (LLMs) seeks to suppress potentially harmful forms of mind-attribution such as models asserting their own consciousness or claiming to experience emotions. We investigate whether suppressing mind-attribution tendencies degrades intimately related socio-cognitive abilities such as Theory of Mind (ToM). Through safety ablation and mechanistic analyses of representational similarity, we demonstrate that LLM attributions of mind to themselves and to technological artefacts are behaviorally and mechanistically dissociable from ToM capabilities. Nevertheless, safety fine-tuned models under-attribute mind to non-human animals relative to human baselines and are less likely to exhibit spiritual belief, suppressing widely shared perspectives regarding the distribution and nature of non-human minds. Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.28925 [cs.CL]   (or arXiv:2603.28925v1 [cs.CL] for this version)   https://doi.org/10.48550/arX...