{"id":"W7106612763","doi":"10.1016/j.procs.2025.10.207","title":"Multi-label classification of evolving psychosocial concerns using prompt-based large language models","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Mental Health via Writing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Rimouski","funders":"","keywords":"Subcategory; Task (project management); Language model; Psychosocial; Language understanding","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":[],"consensus_categories":[],"category_scores_codex":[0.0009327352,0.000132402,0.0001932771,0.0002621696,0.000309118,0.00005506813,0.0005654928,0.00007666245,0.00003461788],"category_scores_gemma":[0.00005019963,0.0001394833,0.0000331863,0.001051789,0.0002687356,0.0003150345,0.0001275336,0.0001656605,0.00001156412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001886964,"about_ca_system_score_gemma":0.0005276648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000926592,"about_ca_topic_score_gemma":0.00001780935,"domain_scores_codex":[0.9981056,0.00006616974,0.0004061163,0.0005694377,0.0003441879,0.0005084907],"domain_scores_gemma":[0.9989866,0.0000925752,0.0002354628,0.0003257688,0.00026363,0.00009594827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003017224,0.005807747,0.1225829,0.003285952,0.0001019198,0.00003164069,0.0814597,0.001239398,0.3675101,0.1043862,0.003060597,0.3102321],"study_design_scores_gemma":[0.001139508,0.0000421808,0.0147312,0.0002035708,0.000007708137,0.000001700684,0.0004368105,0.981817,0.001324354,0.0001666976,0.00001108712,0.0001182046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4063517,0.0002186541,0.5902463,0.000165769,0.001052537,0.0004852772,0.00001148374,0.00008298777,0.001385264],"genre_scores_gemma":[0.8211036,5.182466e-7,0.1782472,0.0004430004,0.000116714,0.00003438348,0.000002965249,0.000009046239,0.00004259228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9805776,"threshold_uncertainty_score":0.5687965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1109102422659512,"score_gpt":0.4368632485065511,"score_spread":0.3259530062405999,"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."}}