{"id":"W7106794650","doi":"10.48448/ce2y-w335","title":"Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmarking; Benchmark (surveying); Trustworthiness; Generative grammar; Generative 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":[0.00787119,0.001433785,0.0006942598,0.002038197,0.0008124809,0.0025627,0.002661699,0.002373665,0.006234265],"category_scores_gemma":[0.03807346,0.000454658,0.0007896913,0.0009381057,0.001570175,0.003129174,0.004093093,0.001689571,0.002936737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001067406,"about_ca_system_score_gemma":0.0009238357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003584984,"about_ca_topic_score_gemma":0.005034563,"domain_scores_codex":[0.9932222,0.003248679,0.0004380525,0.001486545,0.001318562,0.0002859949],"domain_scores_gemma":[0.9811267,0.01053505,0.0007721704,0.004662762,0.00216322,0.0007401162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002251851,0.001145475,0.02287881,0.002665594,0.0005895555,0.001401094,0.006959545,0.1677062,0.04055273,0.009398563,0.07487157,0.669579],"study_design_scores_gemma":[0.0005271193,0.001616343,0.01089885,0.0001983006,0.0001648601,0.0008165784,0.002607192,0.8543684,0.0569756,0.0123229,0.05927895,0.0002248412],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5637321,0.003950849,0.2946771,0.002079431,0.001003623,0.001725709,0.008970742,0.09827404,0.02558635],"genre_scores_gemma":[0.7881487,0.0003318625,0.1813729,0.000684821,0.0001238105,0.0005728994,0.01799308,0.002708816,0.008063082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00787119,"threshold_uncertainty_score":0.04162735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03214465639727791,"score_gpt":0.3083606911927609,"score_spread":0.276216034795483,"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."}}