{"id":"W4416034065","doi":"10.18653/v1/2025.findings-emnlp.1067","title":"Stop Playing the Guessing Game! Evaluating Conversational Recommender Systems via Target-free User Simulation","year":2025,"lang":"","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Recommender system; User modeling; Key (lock); Matching (statistics)","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":[0.009993166,0.0009751292,0.00078614,0.0005377413,0.0004083449,0.001353791,0.001136628,0.0009957744,0.002911614],"category_scores_gemma":[0.04081649,0.0004227802,0.0005137836,0.0003074141,0.0005730328,0.001982337,0.001639647,0.001002374,0.001009798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005570751,"about_ca_system_score_gemma":0.000598423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001763412,"about_ca_topic_score_gemma":0.002679024,"domain_scores_codex":[0.9900407,0.007789074,0.000456484,0.0005357021,0.0009616135,0.0002163239],"domain_scores_gemma":[0.9645514,0.02794484,0.0010249,0.003587784,0.002135008,0.0007561119],"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":[0.01296164,0.005463093,0.06867675,0.003372696,0.001556658,0.001008112,0.009500121,0.2581095,0.1128177,0.0236431,0.01467245,0.4882182],"study_design_scores_gemma":[0.0007378191,0.007417825,0.01575369,0.0001836358,0.0002388149,0.0003515873,0.001326381,0.9137909,0.04102576,0.009661242,0.009286896,0.0002254248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8076733,0.0005025693,0.1808951,0.0003390599,0.00007426342,0.001053095,0.0007667715,0.002264362,0.006431477],"genre_scores_gemma":[0.9080813,0.0001282911,0.08842106,0.0001501555,0.00001409331,0.0006405716,0.0006149206,0.0001089459,0.001840694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009993166,"threshold_uncertainty_score":0.05284953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06331105928617485,"score_gpt":0.3454273776207131,"score_spread":0.2821163183345383,"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."}}