{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007473385,0.000111241,0.000102992,0.0001045908,0.0001064618,0.0004955441,0.0001795861,0.00003767523,0.00002132451],"category_scores_gemma":[0.0001165822,0.00009492076,0.00003609414,0.0001920135,0.00001620005,0.000511162,0.0001603378,0.0001078372,0.00001184013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001735589,"about_ca_system_score_gemma":0.00008198855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005208025,"about_ca_topic_score_gemma":0.000002418114,"domain_scores_codex":[0.9987507,0.0001184647,0.0001962417,0.0004986761,0.0002602178,0.000175735],"domain_scores_gemma":[0.9994264,0.0001120847,0.00002912647,0.0002369057,0.0001324036,0.00006306476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006055153,0.00008993187,0.00005460442,0.00007703684,0.0002471592,0.0001258561,0.04856674,0.04051151,0.4218934,0.3432189,0.0009996812,0.1441546],"study_design_scores_gemma":[0.0001973996,0.00009231034,0.000009604444,0.00005201695,0.00001097482,0.00001876662,0.00044846,0.9873821,0.01053816,0.001122704,0.00001822243,0.0001093536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02661722,0.0020079,0.9685001,0.001288789,0.0003813202,0.0002798163,3.422238e-7,0.0002776322,0.0006468561],"genre_scores_gemma":[0.5677599,0.00003285089,0.4314257,0.000182707,0.00009227486,0.000009582989,4.963393e-7,0.000007343841,0.0004890942],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9468705,"threshold_uncertainty_score":0.4778543,"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."}}