{"id":"W4409767075","doi":"10.1145/3706598.3714097","title":"To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Psychological intervention; Risk analysis (engineering); Natural language processing; Artificial intelligence; Psychology; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01310634,0.001043398,0.0007998248,0.0006596932,0.0005840701,0.001677608,0.00173129,0.002226075,0.006331669],"category_scores_gemma":[0.2326144,0.0004636028,0.0004717777,0.0003236505,0.001334216,0.004431373,0.001844092,0.003004166,0.001531119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000852834,"about_ca_system_score_gemma":0.003081808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001785425,"about_ca_topic_score_gemma":0.001540905,"domain_scores_codex":[0.989059,0.007001215,0.0006075141,0.001284252,0.001460284,0.0005877002],"domain_scores_gemma":[0.7600682,0.2066831,0.01279714,0.0104445,0.004659504,0.005347586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.06035241,0.03261781,0.1069769,0.002235422,0.001483485,0.0005927311,0.007744156,0.03423363,0.03535801,0.009769855,0.01280385,0.6958318],"study_design_scores_gemma":[0.02035315,0.09356303,0.2186472,0.004029095,0.008992369,0.001485898,0.01509913,0.425246,0.07044984,0.1145698,0.02655299,0.001011514],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9724675,0.0005270084,0.0139692,0.004760894,0.0002645768,0.0007030403,0.0002675333,0.001274258,0.005766032],"genre_scores_gemma":[0.9918267,0.0001542538,0.00606691,0.0006636477,0.00003761405,0.0005734826,0.0001133416,0.00009665197,0.0004674927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01310634,"threshold_uncertainty_score":0.0693137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4626376707382103,"score_gpt":0.5876899920776022,"score_spread":0.1250523213393919,"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."}}