{"id":35134,"date":"2026-04-13T14:10:33","date_gmt":"2026-04-13T14:10:33","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/understanding-artificial-theory-of-mind-perturbed-tasks-and-reasoning-in-large-language-models\/"},"modified":"2026-06-08T13:17:45","modified_gmt":"2026-06-08T13:17:45","slug":"understanding-artificial-theory-of-mind-perturbed-tasks-and-reasoning-in-large-language-models","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/understanding-artificial-theory-of-mind-perturbed-tasks-and-reasoning-in-large-language-models\/","title":{"rendered":"Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language Models"},"content":{"rendered":"<p>Theory of Mind ({ToM}) refers to an agent&#8217;s ability to model the internal states of others. Contributing to the debate whether large language models ({LLMs}) exhibit genuine {ToM} capabilities, our study investigates their {ToM} robustness using perturbations on false-belief tasks and examines the potential of Chain-of-Thought prompting ({CoT}) to enhance performance and explain the {LLM}&#8217;s decision. We introduce a handcrafted, richly annotated {ToM} dataset, including classic and perturbed false belief tasks, the corresponding spaces of valid reasoning chains for correct task completion, subsequent reasoning faithfulness, task solutions, and propose metrics to evaluate reasoning chain correctness and to what extent final answers are faithful to reasoning traces of the generated {CoT}. We show a steep drop in {ToM} capabilities under task perturbation for all evaluated {LLMs}, questioning the notion of any robust form of {ToM} being present. While {CoT} prompting improves the {ToM} performance overall in a faithful manner, it surprisingly degrades accuracy for some perturbation classes, indicating that selective application is necessary.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Theory of Mind ({ToM}) refers to an agent&#8217;s ability to model the internal states of others. Contributing to the debate whether large language models ({LLMs}) exhibit genuine {ToM} capabilities, our study investigates their {ToM} robustness using perturbations on false-belief tasks and examines the potential of Chain-of-Thought prompting ({CoT}) to enhance performance and explain the {LLM}&#8217;s decision. We introduce a handcrafted, richly annotated {ToM} dataset, including classic and perturbed false belief [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[30],"class_list":["post-35134","publication","type-publication","status-publish","hentry","publication-type-article"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/35134","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/12"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/35134\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=35134"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=35134"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}