{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002529532,0.000177552,0.0002998306,0.0005413733,0.0001118399,0.00004171937,0.0004867082,0.00007036226,0.000003398947],"category_scores_gemma":[0.00001003948,0.0001874365,0.0001711921,0.0009297749,0.000006038924,0.0004528079,0.00000613116,0.0001691046,6.640481e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007382341,"about_ca_system_score_gemma":0.0000499396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000525395,"about_ca_topic_score_gemma":0.0004076682,"domain_scores_codex":[0.9987766,0.00002830263,0.0003110213,0.0004202202,0.0002037808,0.0002601033],"domain_scores_gemma":[0.9989226,0.00009206712,0.00004571494,0.0007760332,0.00009581858,0.00006771117],"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":[0.000006990511,0.0002764965,0.00007231625,0.00003888214,0.0002576154,0.000002170189,0.006593287,0.9876061,0.00009021084,0.0005502176,0.000003193845,0.004502525],"study_design_scores_gemma":[0.0005765799,0.0001456687,0.00004401649,0.00002523187,0.0001699246,3.446151e-7,0.001235948,0.9962981,0.001257888,0.00007108886,0.00002535301,0.0001498045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1986096,0.00003577078,0.8003576,0.00001051437,0.0003008109,0.0002871543,0.00003381221,0.0003607275,0.000004006361],"genre_scores_gemma":[0.9552882,0.000001714998,0.04438305,0.00004424746,0.00001721889,0.0001491617,0.000003555399,0.00001528951,0.00009753439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7566786,"threshold_uncertainty_score":0.7643439,"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."}}