{"id":"W4405968021","doi":"10.1109/tse.2024.3519464","title":"<i>Look Before You Leap:</i> An Exploratory Study of Uncertainty Analysis for Large Language Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; Japan Science and Technology Agency; Japan Society for the Promotion of Science","keywords":"Computer science; Exploratory analysis; Programming language; Exploratory research; Data science; Software 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01557717,0.001038904,0.0007150014,0.001927442,0.001315544,0.004187532,0.002055027,0.002111913,0.003232282],"category_scores_gemma":[0.11879,0.0006078221,0.001323912,0.001527826,0.003764999,0.0117757,0.003453978,0.006389223,0.0007567147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00197252,"about_ca_system_score_gemma":0.00164427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006161577,"about_ca_topic_score_gemma":0.006248746,"domain_scores_codex":[0.9890023,0.007069732,0.0003392109,0.001045575,0.002293453,0.0002497173],"domain_scores_gemma":[0.8517069,0.1302558,0.003480237,0.00767905,0.005991311,0.000886794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000904364,0.0005586096,0.05925454,0.002173929,0.0009347508,0.001651604,0.0215337,0.1159967,0.01959825,0.2571994,0.04419011,0.4760041],"study_design_scores_gemma":[0.00008329784,0.0006832081,0.02248672,0.001027817,0.0001764455,0.001245502,0.006654879,0.5717868,0.02046367,0.3079142,0.06708784,0.0003895363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.168375,0.004524013,0.7834773,0.02758955,0.000388861,0.0005049855,0.00110629,0.001732522,0.01230147],"genre_scores_gemma":[0.7440749,0.001781648,0.2438097,0.004241113,0.0004161991,0.00067152,0.00135521,0.000761191,0.002888424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01557717,"threshold_uncertainty_score":0.08238101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01670240554815756,"score_gpt":0.252028520668388,"score_spread":0.2353261151202305,"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."}}