{"id":"W4412377058","doi":"10.1145/3726302.3730090","title":"The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute of Standards and Technology; Ministry of Science and ICT, South Korea; Institute for Information and Communications Technology Promotion; Universitas Brawijaya","keywords":"Computer science; Recall; Natural language processing; Language model; Extraction (chemistry); Artificial intelligence; Programming language; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.03905755,0.00216259,0.00143202,0.004772114,0.001430042,0.00572159,0.003274892,0.002464719,0.002978078],"category_scores_gemma":[0.09082968,0.001312456,0.001926969,0.002103268,0.001753732,0.009182416,0.005418842,0.003613322,0.001971903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002669911,"about_ca_system_score_gemma":0.003591433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0107606,"about_ca_topic_score_gemma":0.01844313,"domain_scores_codex":[0.9563439,0.02875964,0.002416485,0.005049307,0.006550512,0.0008801983],"domain_scores_gemma":[0.9064419,0.06230911,0.004729796,0.01712397,0.008164284,0.001230947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001223578,0.0008490197,0.03402624,0.001733461,0.001205343,0.0006264597,0.006858351,0.08429731,0.04607214,0.0202893,0.03318368,0.7696351],"study_design_scores_gemma":[0.0002270361,0.0007050997,0.01447323,0.0002976457,0.000379666,0.0005020183,0.00113755,0.8609992,0.06387925,0.02427732,0.03279994,0.0003220626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1165863,0.001584725,0.8235809,0.00128641,0.0002056549,0.000968109,0.002408298,0.04770422,0.005675434],"genre_scores_gemma":[0.4496185,0.0002291503,0.5386385,0.0004822854,0.00008335891,0.0006310863,0.005798356,0.00270252,0.001816219],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03905755,"threshold_uncertainty_score":0.2065585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0236931126214044,"score_gpt":0.3102502773306289,"score_spread":0.2865571647092245,"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."}}