{"id":"W7160819649","doi":"10.66372/jger.v3i1.4","title":"Evaluating the Quality of Large Language Model-Generated Explanations in Recommendation Tasks: A Multi-Dimensional Comparative Analysis","year":2025,"lang":"","type":"article","venue":"Journal of Global Engineering Review","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Quality (philosophy); Annotation; Natural language; Recommender system; Language model","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":[0.04007811,0.0009340904,0.001032621,0.004758475,0.0005850705,0.003000415,0.001260315,0.001513769,0.001533248],"category_scores_gemma":[0.1982933,0.0004017327,0.001753102,0.002918356,0.0008324094,0.003197592,0.001854486,0.001571306,0.0004594469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001696897,"about_ca_system_score_gemma":0.001328714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003080249,"about_ca_topic_score_gemma":0.005054724,"domain_scores_codex":[0.9674603,0.02446333,0.002153318,0.001721692,0.003929817,0.0002715768],"domain_scores_gemma":[0.6494172,0.3163164,0.008290055,0.01096996,0.01423821,0.0007680916],"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":[0.003979939,0.0008668967,0.06851603,0.008114499,0.003088372,0.0002783638,0.006157413,0.06806215,0.00868855,0.005849026,0.009143049,0.8172557],"study_design_scores_gemma":[0.001308291,0.005863299,0.1620121,0.003715787,0.004166352,0.0009207867,0.006315524,0.7090903,0.03747021,0.03126729,0.03694955,0.0009204377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6604918,0.02327596,0.2945252,0.00242954,0.0002135659,0.001725882,0.005246315,0.004750584,0.007341194],"genre_scores_gemma":[0.779699,0.002889884,0.2077063,0.0002754696,0.00008298434,0.0009689208,0.007200683,0.0002773956,0.0008994487],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04007811,"threshold_uncertainty_score":0.2119559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1448898721347533,"score_gpt":0.4794434752699744,"score_spread":0.3345536031352211,"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."}}