{"id":"W4403511562","doi":"10.1109/iv64223.2024.00051","title":"Detecting Multiple Mental Health Disorders with Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Mental Health via Writing","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Mental health; Natural language processing; Artificial intelligence; Psychology; Psychiatry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004264278,0.0001401916,0.0001469982,0.00009233173,0.0002218279,0.00003703169,0.00009148847,0.00004812868,0.001106356],"category_scores_gemma":[0.000005032066,0.0001137468,0.00003848268,0.000203181,0.00002080448,0.0001363095,0.00004449046,0.0002428036,0.0003274831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00013416,"about_ca_system_score_gemma":0.00004636611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002712294,"about_ca_topic_score_gemma":0.006154724,"domain_scores_codex":[0.9985011,0.00009436004,0.0002426648,0.0003806788,0.000164709,0.0006165226],"domain_scores_gemma":[0.9994893,0.0001130381,0.00003953636,0.0002041617,0.000005517649,0.0001484337],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004665917,0.0009291237,0.02481827,0.001861232,0.000341232,0.0001958169,0.2269475,0.0001210069,0.0006584752,0.0834364,0.02139803,0.6388263],"study_design_scores_gemma":[0.01145112,0.003042083,0.0061139,0.001940673,0.00004683145,0.0006215729,0.5259675,0.3883778,0.0009719522,0.002054713,0.05722805,0.002183734],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8142254,0.006428269,0.03093372,0.004194486,0.001300295,0.001334104,0.0001183444,0.001301276,0.1401641],"genre_scores_gemma":[0.9930357,0.00001379656,0.002259195,0.001330437,0.00009177977,0.00005984894,0.00003043627,0.00005199276,0.003126752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6366425,"threshold_uncertainty_score":0.9998068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02614741108691208,"score_gpt":0.3746934120347203,"score_spread":0.3485460009478082,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}