{"id":"W4400909682","doi":"10.1109/icde60146.2024.00466","title":"Towards Explainability in Retrieval-Augmented LLMs","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0004908092,0.00006972458,0.00008153287,0.00009538403,0.00001845862,0.0001404189,0.0004099756,0.00003883238,0.00008224093],"category_scores_gemma":[0.00005894772,0.00005747033,0.00003493571,0.0004822873,0.00001225798,0.0003564564,0.0002132935,0.0001159413,0.00006360412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001165522,"about_ca_system_score_gemma":0.00009499976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001289631,"about_ca_topic_score_gemma":0.00002108891,"domain_scores_codex":[0.9990409,0.00003582633,0.0001771234,0.0003731852,0.0001890591,0.000183881],"domain_scores_gemma":[0.9994502,0.00004327182,0.000007564812,0.0004332176,0.0000219085,0.00004380415],"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":[0.000008937168,0.00008687206,0.001534203,0.0001370161,0.00001343053,0.000183399,0.003074746,0.000534416,0.00127378,0.6811545,0.001468785,0.3105299],"study_design_scores_gemma":[0.0001306195,0.00002734456,0.002118077,0.00003905574,0.000001129156,0.000007473185,0.00005039054,0.9535738,0.003781553,0.03382196,0.006311042,0.0001375381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1046132,0.0002234663,0.8766592,0.003558809,0.0005582996,0.0001105371,3.033793e-7,0.0004001332,0.01387599],"genre_scores_gemma":[0.9702151,0.000006324072,0.02849869,0.0001846415,0.00003426251,0.000004658562,3.550995e-7,0.000003723669,0.001052281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9530394,"threshold_uncertainty_score":0.2343572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02583037272530825,"score_gpt":0.2820160440700754,"score_spread":0.2561856713447672,"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."}}