{"id":"W4407570660","doi":"10.1145/3706598.3714020","title":"Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"Princeton University; National Science Foundation","keywords":"Key (lock); Computer science; Scale (ratio); Raising (metalworking); Cognitive psychology; Psychology; Computer security; 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":[0.0003907927,0.0001543211,0.0002078149,0.0001145905,0.0000964325,0.0001181106,0.0009348167,0.0001060983,0.000002537834],"category_scores_gemma":[0.00003895709,0.0001096096,0.00005408348,0.00009843906,0.0000278646,0.0001144777,0.004408511,0.0002844963,0.000001291196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002398618,"about_ca_system_score_gemma":0.00008927209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003299306,"about_ca_topic_score_gemma":0.00009475103,"domain_scores_codex":[0.9988353,0.00006681993,0.0002739474,0.0004351863,0.000224369,0.0001643549],"domain_scores_gemma":[0.9986804,0.0001201576,0.0001436795,0.0009696244,0.00005867205,0.00002746374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008217212,0.00005868444,0.0001914467,0.0003425974,0.00007553715,0.000004081343,0.02218107,0.0589352,0.0002202669,0.7130904,0.00008030929,0.2048122],"study_design_scores_gemma":[0.00009843393,0.000007968543,0.00003316893,0.0002319827,0.000007857385,0.000001735767,0.00131978,0.9134275,0.0009420736,0.08344094,0.0003597691,0.0001287703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03472158,0.005047185,0.9163738,0.001117107,0.0002863652,0.0003943393,0.00003344406,0.0001862966,0.04183987],"genre_scores_gemma":[0.9432021,0.000175414,0.05529609,0.0003251047,0.00003724729,0.00004537392,0.000003933112,0.000005973108,0.000908706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9084806,"threshold_uncertainty_score":0.5494894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03481069476889895,"score_gpt":0.2591592520451504,"score_spread":0.2243485572762514,"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."}}