{"id":"W4392846357","doi":"10.1007/978-3-031-56060-6_26","title":"Adapting Standard Retrieval Benchmarks to Evaluate Generated Answers","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Artificial intelligence","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002386978,0.000688204,0.0006568168,0.001234709,0.000286832,0.00132829,0.003801139,0.0003840243,0.00006636224],"category_scores_gemma":[0.0001951093,0.0006384969,0.0001683971,0.001353693,0.0002815132,0.0005268062,0.002440935,0.001264236,0.0001055507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008334798,"about_ca_system_score_gemma":0.001179934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002698539,"about_ca_topic_score_gemma":0.00006258886,"domain_scores_codex":[0.9934987,0.00004656647,0.0007696523,0.002653993,0.002035076,0.00099601],"domain_scores_gemma":[0.9968411,0.0002975795,0.0001916826,0.001825582,0.0004778252,0.0003662345],"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":[0.0000239352,0.000008734763,0.000008825386,0.00006413253,0.00002916025,0.0003107719,0.001782296,0.4175209,0.0008457481,0.03192362,0.0001273592,0.5473545],"study_design_scores_gemma":[0.0001750342,0.0002236317,0.000005515743,0.0006431974,0.00001458508,0.00005336014,3.050787e-7,0.8981315,0.001884681,0.09415621,0.003957358,0.0007546468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005026416,0.0008137889,0.9845203,0.002088788,0.004814702,0.0005459111,0.00001140492,0.0003045667,0.006397942],"genre_scores_gemma":[0.110801,0.00003622779,0.8835915,0.002652937,0.00132543,0.000008848306,0.00001126951,0.00008338359,0.001489309],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5465999,"threshold_uncertainty_score":0.9997084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02661892328597793,"score_gpt":0.2743444726809662,"score_spread":0.2477255493949883,"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."}}