{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003410154,0.002092182,0.001239639,0.002265146,0.0007089255,0.001739802,0.00282885,0.001160755,0.00489074],"category_scores_gemma":[0.02211322,0.0006527437,0.0008963281,0.001167516,0.0007579128,0.002754302,0.00327131,0.001364743,0.002398876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001149572,"about_ca_system_score_gemma":0.001469553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004539392,"about_ca_topic_score_gemma":0.006106475,"domain_scores_codex":[0.9959283,0.002090082,0.0002469329,0.0007815512,0.000730618,0.0002224558],"domain_scores_gemma":[0.9888275,0.006756993,0.0004036657,0.002018052,0.001690155,0.0003037944],"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":[0.001869318,0.0008376754,0.004778986,0.001165181,0.0002097138,0.000816551,0.001438316,0.2329872,0.0390308,0.009083797,0.04471408,0.6630684],"study_design_scores_gemma":[0.0001648005,0.0002496626,0.0007474704,0.00002982591,0.00005935042,0.00009229151,0.0003186364,0.9578103,0.02260318,0.009819552,0.008062644,0.00004219076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0931278,0.0006280868,0.7810889,0.0005263693,0.0002143479,0.000959839,0.002766921,0.1145603,0.006127271],"genre_scores_gemma":[0.5247341,0.0001654682,0.4511634,0.0002994257,0.00006845826,0.001105446,0.01424265,0.004989411,0.003231558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00489074,"threshold_uncertainty_score":0.01803488,"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."}}