{"id":"W4406771321","doi":"10.1007/978-981-96-1024-2_8","title":"Evaluation of Retrieval-Augmented Generation: A Survey","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Topic Modeling","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Information retrieval; Computer science; Thesaurus; Natural language processing","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":[0.008081684,0.0001523845,0.0002239891,0.001017277,0.000237872,0.0002790888,0.002596719,0.0001106744,0.000008479225],"category_scores_gemma":[0.0003055508,0.0001606611,0.00003318388,0.0006354565,0.0003581288,0.003797325,0.001844932,0.0002411059,0.000007952628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002388694,"about_ca_system_score_gemma":0.001180487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002927326,"about_ca_topic_score_gemma":0.000037123,"domain_scores_codex":[0.9974639,0.0001518403,0.0008334985,0.0002716121,0.001140518,0.0001385723],"domain_scores_gemma":[0.9944987,0.0002106215,0.0004061956,0.002399927,0.00243555,0.0000489643],"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":[0.000001632966,0.00001418125,0.00005306614,0.00002160215,0.00001051872,4.052156e-8,0.0007842046,0.002074477,0.000009586058,0.5188041,0.0003039443,0.4779227],"study_design_scores_gemma":[0.0002654575,0.00001900974,0.001091694,0.0001309411,0.00001140513,0.000002245238,0.000003218822,0.9885802,0.00003605885,0.004298251,0.005421731,0.0001398102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001851661,0.0007269014,0.8396555,0.0004626238,0.0004575291,0.0005456125,0.00001836509,0.00004438149,0.1579039],"genre_scores_gemma":[0.469556,0.005309371,0.5185835,0.001637741,0.0001239328,0.00006736978,0.0004831799,0.00001841653,0.004220487],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9865057,"threshold_uncertainty_score":0.655157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1711046492460147,"score_gpt":0.3563433662537061,"score_spread":0.1852387170076915,"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."}}