{"id":"W4408120198","doi":"10.1145/3704137.3704181","title":"Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Perspective (graphical); Computer science; Content (measure theory); Information retrieval; Artificial intelligence; Mathematics","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":[0.006674171,0.00128273,0.001615124,0.001442399,0.0005387831,0.003044235,0.002139042,0.00213475,0.003114613],"category_scores_gemma":[0.02227994,0.0006474353,0.0009264263,0.001485675,0.0008732466,0.003093775,0.00148734,0.001043163,0.001000418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001436695,"about_ca_system_score_gemma":0.002031474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006836995,"about_ca_topic_score_gemma":0.00819753,"domain_scores_codex":[0.9943672,0.003652421,0.0002486715,0.0004984968,0.0008620071,0.0003712219],"domain_scores_gemma":[0.9874268,0.00926495,0.0003903959,0.001531483,0.001162921,0.0002233368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001221669,0.0005921368,0.005011757,0.0005843386,0.0002712285,0.0001724092,0.0002772622,0.6534196,0.01643263,0.01145442,0.005110586,0.305452],"study_design_scores_gemma":[0.0000665239,0.0003113347,0.0006878151,0.00001383946,0.0001245285,0.00005554766,0.00008835571,0.9840329,0.007788321,0.005290663,0.001520104,0.00002004636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.197691,0.003829001,0.7743899,0.001503209,0.0001571915,0.0007879545,0.0007378163,0.007580192,0.0133238],"genre_scores_gemma":[0.689595,0.0006883971,0.304233,0.0002354446,0.0001188621,0.0001689391,0.00109859,0.0006370902,0.003224739],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006836995,"threshold_uncertainty_score":0.0352968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1633340000320916,"score_gpt":0.3343451455154014,"score_spread":0.1710111454833098,"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."}}