{"id":"W4400582230","doi":"10.1145/3660810","title":"ClarifyGPT: A Framework for Enhancing LLM-Based Code Generation via Requirements Clarification","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Consistency (knowledge bases); Computer science; Fidelity; Code (set theory); Natural language generation; Natural language; Artificial intelligence; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008599681,0.000259615,0.0002175311,0.0003167557,0.0001192699,0.0003143913,0.00254526,0.0002352793,0.000003881813],"category_scores_gemma":[0.01296562,0.0002220886,0.0001736476,0.0009865756,0.00002707287,0.0004660059,0.0003935065,0.0005386418,0.00001334792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002386038,"about_ca_system_score_gemma":0.00009464208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003298545,"about_ca_topic_score_gemma":6.106878e-7,"domain_scores_codex":[0.9979225,0.000006327022,0.0003847815,0.0005935379,0.0006674491,0.0004254233],"domain_scores_gemma":[0.9975293,0.001054314,0.00009984226,0.0008922251,0.0003288394,0.00009551825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001115108,0.0005969439,0.009687219,0.007389142,0.0005422951,0.000006943785,0.002483192,0.0788905,0.5526459,0.2832226,0.02306916,0.04135454],"study_design_scores_gemma":[0.0003070275,0.0002869369,0.002875742,0.001080704,0.00003348808,0.000007242508,0.000005417576,0.549941,0.4341579,0.006088183,0.004739659,0.0004767287],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03672688,0.0002661669,0.9588242,0.001171299,0.00125983,0.0006028322,0.00001169203,0.001133522,0.000003584977],"genre_scores_gemma":[0.5343672,0.000003947498,0.4649608,0.00009698335,0.0002496477,0.0002193616,0.000004476969,0.00005385274,0.00004373034],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4976403,"threshold_uncertainty_score":0.9953486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03864211965604995,"score_gpt":0.2956780983054859,"score_spread":0.2570359786494359,"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."}}