{"id":"W4414093251","doi":"10.3390/make7030097","title":"A Review of Large Language Models for Automated Test Case Generation","year":2025,"lang":"en","type":"review","venue":"Machine Learning and Knowledge Extraction","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Test (biology); Natural language generation; Natural language; Focus (optics); Software; Test case","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":[0.001137592,0.0002832668,0.0008516959,0.0002892007,0.0002284597,0.00006707022,0.0001909421,0.0001935804,0.000002633662],"category_scores_gemma":[0.002078264,0.0002423487,0.0002119202,0.000468014,0.00001388474,0.0001727093,0.0001328248,0.0004010916,0.000002877789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005288522,"about_ca_system_score_gemma":0.0001874919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005743802,"about_ca_topic_score_gemma":0.00001622399,"domain_scores_codex":[0.9984621,0.0002983053,0.0005207765,0.0004503125,0.00007900445,0.0001894449],"domain_scores_gemma":[0.9975311,0.001467167,0.0004618606,0.0003139007,0.0001782579,0.00004770373],"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":[3.757435e-7,0.00006575992,0.000001330752,0.09084979,0.0000171212,0.00001672944,0.00009144425,0.000002840266,9.093586e-7,0.0001528649,0.006473173,0.9023277],"study_design_scores_gemma":[0.00009291365,0.00008041471,8.198179e-8,0.06901033,0.0002160958,0.0007120132,0.000001203021,0.4985284,0.000001852271,0.00007543867,0.4310791,0.0002022051],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.788069e-7,0.7571058,0.237969,0.00001378794,0.0001506445,0.0004725654,0.0000250296,0.00397602,0.0002870263],"genre_scores_gemma":[0.00004325447,0.9666857,0.03197354,0.00002828683,0.0001104247,0.0001843322,0.0001968688,0.00002361325,0.0007539599],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9021255,"threshold_uncertainty_score":0.9882692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04220589820370538,"score_gpt":0.4041485293505684,"score_spread":0.361942631146863,"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."}}