{"id":"W4407355838","doi":"10.1145/3709681","title":"Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Information retrieval; Geography","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005202746,0.0001471437,0.0001932192,0.0001363181,0.0000891302,0.00007747607,0.006153954,0.00003867613,0.000003137227],"category_scores_gemma":[0.0001466202,0.00010435,0.00003838901,0.0007530021,0.00005539185,0.0006152577,0.005792634,0.0001100291,0.000002167821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004401978,"about_ca_system_score_gemma":0.000017395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002812255,"about_ca_topic_score_gemma":0.00000605031,"domain_scores_codex":[0.9986154,0.00001655567,0.0002701757,0.0005896713,0.0003500614,0.0001580711],"domain_scores_gemma":[0.9976025,0.00007593901,0.0002418692,0.001891936,0.0001624923,0.00002523936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002796657,0.0006514191,0.006349735,0.0006581987,0.001108804,0.000001631308,0.000673467,0.000212454,0.01546521,0.7900328,0.04309121,0.1414754],"study_design_scores_gemma":[0.007811243,0.0009588785,0.08664086,0.005183322,0.001200443,0.000001756379,0.0007614331,0.4384032,0.2328154,0.2037312,0.0211964,0.001295909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7480225,0.001214944,0.1948229,0.01036244,0.001951523,0.009477723,0.0003121129,0.0003120474,0.03352378],"genre_scores_gemma":[0.9166248,0.0001186249,0.0825082,0.0001772001,0.00004682014,0.00006750586,0.00007119904,0.00001006759,0.0003755933],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5863016,"threshold_uncertainty_score":0.9992232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05128988014828679,"score_gpt":0.2954122021952202,"score_spread":0.2441223220469334,"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."}}