{"id":"W7126443349","doi":"10.18653/v1/2024.clpsych-1.15","title":"Overview of the CLPsych 2024 Shared Task: Leveraging Large Language Models to Identify Evidence of Suicidality Risk in Online Posts","year":2024,"lang":"","type":"article","venue":"","topic":"Mental Health via Writing","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Atomic Energy of Canada Limited; Bar-Ilan University; UK Research and Innovation; National Science Foundation","keywords":"Computational linguistics; The Internet; Poison control; On Language; Computational model; Identification (biology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01216065,0.004034945,0.002353297,0.005229176,0.0019661,0.005207554,0.0038373,0.004254433,0.02191741],"category_scores_gemma":[0.02751974,0.001652988,0.003075941,0.00236016,0.0009664412,0.004496314,0.007985743,0.004396978,0.02853716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001024192,"about_ca_system_score_gemma":0.004545933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009996209,"about_ca_topic_score_gemma":0.0200047,"domain_scores_codex":[0.9931526,0.003864036,0.0004737075,0.001338973,0.0009080308,0.0002625547],"domain_scores_gemma":[0.9854825,0.009093939,0.0003902884,0.002545392,0.001233759,0.001254164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001358187,0.00144705,0.01380449,0.003071927,0.0013298,0.0008381605,0.001105319,0.007025992,0.01729118,0.003107719,0.4282427,0.5213776],"study_design_scores_gemma":[0.002952229,0.002467727,0.05485366,0.001765606,0.00193426,0.003811945,0.002605373,0.3792304,0.02883246,0.08968139,0.4301869,0.001678099],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05812709,0.01964814,0.525512,0.01289433,0.003094758,0.008099345,0.2273203,0.1219281,0.02337597],"genre_scores_gemma":[0.1411484,0.003529914,0.3981347,0.003244823,0.001514871,0.009983499,0.4206928,0.006776372,0.01497458],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02191741,"threshold_uncertainty_score":0.07332104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1862968720971332,"score_gpt":0.4930726363834393,"score_spread":0.306775764286306,"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."}}