{"id":"W4396802056","doi":"10.1145/3630106.3658941","title":"\"I'm Not Sure, But...\": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"Microsoft Research; Universitas Brawijaya; National Science Foundation","keywords":"Scale (ratio); Task (project management); Natural experiment; Expression (computer science); Psychology; Perspective (graphical); Computer science; Social psychology; Cognitive psychology; Artificial intelligence; Medicine; Engineering","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":[0.0007756854,0.0003304917,0.0003735341,0.0001331054,0.0000824387,0.0002332993,0.001175453,0.0002384475,0.00002416198],"category_scores_gemma":[0.00006044743,0.0001894133,0.0001536482,0.0001518383,0.00004135718,0.0001442426,0.003205484,0.0008537733,0.000008563407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008438245,"about_ca_system_score_gemma":0.0001729384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00162,"about_ca_topic_score_gemma":0.00002844123,"domain_scores_codex":[0.9978377,0.000124755,0.0003853474,0.0008784554,0.0004278564,0.000345848],"domain_scores_gemma":[0.9977922,0.0002265339,0.0001753132,0.001649234,0.00006988212,0.00008676775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000888307,0.0001695756,0.0007581778,0.0006322355,0.0001921367,0.00009220946,0.01886221,0.8695356,0.009657688,0.06993795,0.003822686,0.02625067],"study_design_scores_gemma":[0.0001977122,0.00005557495,0.0008292492,0.0006384953,0.00001136945,0.000005205871,0.0002079089,0.9893098,0.002644995,0.005817658,0.00002829435,0.0002537428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7813547,0.0008151847,0.2127213,0.0002768556,0.0004355512,0.0003140194,0.00005495619,0.0002006331,0.003826752],"genre_scores_gemma":[0.9858386,0.0000834056,0.01219652,0.000153609,0.0001177341,0.00002543219,0.000005990486,0.00002504167,0.001553651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2044839,"threshold_uncertainty_score":0.7724048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04877756425759006,"score_gpt":0.3127205170671762,"score_spread":0.2639429528095861,"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."}}