{"id":32568,"date":"2026-01-21T17:02:12","date_gmt":"2026-01-21T17:02:12","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/explaining-gpt-4s-schema-of-depression-using-machine-behavior-analysis\/"},"modified":"2026-09-17T11:24:50","modified_gmt":"2026-09-17T11:24:50","slug":"explaining-gpt-4s-schema-of-depression-using-machine-behavior-analysis","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/explaining-gpt-4s-schema-of-depression-using-machine-behavior-analysis\/","title":{"rendered":"Explaining GPT-4&#8217;s Schema of Depression Using Machine Behavior Analysis"},"content":{"rendered":"<p>Use of large language models such as ChatGPT (GPT-4) for mental health support has grown rapidly, emerging as a promising route to assess and help people with mood disorders, like depression. However, we have a limited understanding of GPT-4&#8217;s schema of mental disorders, that is, how it internally associates and interprets symptoms. In this work, we leveraged contemporary measurement theory to decode how GPT-4 interrelates depressive symptoms to inform both clinical utility and theoretical understanding. We found GPT-4&#8217;s assessment of depression: (a) had high overall convergent validity (r = .71 with self-report on 955 samples, and r = .81 with experts judgments on 209 samples); (b) had moderately high internal consistency (symptom inter-correlates r = .23 to .78 ) that largely aligned with literature and self-report; except that GPT-4 (c) underemphasized suicidality&#8217;s &#8212; and overemphasized psychomotor&#8217;s &#8212; relationship with other symptoms, and (d) had symptom inference patterns that suggest nuanced hypotheses (e.g. sleep and fatigue are influenced by most other symptoms while feelings of worthlessness\/guilt is mostly influenced by depressed mood).<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Use of large language models such as ChatGPT (GPT-4) for mental health support has grown rapidly, emerging as a promising route to assess and help people with mood disorders, like depression. However, we have a limited understanding of GPT-4&#8217;s schema of mental disorders, that is, how it internally associates and interprets symptoms. In this work, we leveraged contemporary measurement theory to decode how GPT-4 interrelates depressive symptoms to inform both [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[30],"class_list":["post-32568","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\/32568","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\/14"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32568\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=32568"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=32568"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}