{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006709022,0.002595332,0.0008013883,0.002339753,0.0008374864,0.002088094,0.004376793,0.002429598,0.008730297],"category_scores_gemma":[0.03096388,0.001738982,0.002457153,0.0009517119,0.002165008,0.00384207,0.004982915,0.004555638,0.004555242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001476967,"about_ca_system_score_gemma":0.003922198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005099506,"about_ca_topic_score_gemma":0.007589884,"domain_scores_codex":[0.9939719,0.002490896,0.0005322197,0.00100287,0.001672058,0.0003300187],"domain_scores_gemma":[0.9860563,0.007746659,0.001207017,0.003137078,0.001398855,0.0004541219],"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":[0.0008521608,0.001001727,0.004929382,0.003006551,0.0002532481,0.001640172,0.004990538,0.07796579,0.06808623,0.07060592,0.08247399,0.6841943],"study_design_scores_gemma":[0.0004310609,0.0005191974,0.001237891,0.0004503567,0.0001206607,0.001111568,0.0005765189,0.7162777,0.06127133,0.05199287,0.1657359,0.0002749793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003305926,0.0001313153,0.9238024,0.0003486057,0.00005880304,0.0005660151,0.000439071,0.06945139,0.001896429],"genre_scores_gemma":[0.03692972,0.0001377959,0.9513541,0.0003752043,0.00002676338,0.0006471363,0.001902515,0.006736129,0.001890543],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008730297,"threshold_uncertainty_score":0.03548115,"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."}}