{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007389854,0.002062441,0.001657046,0.006582758,0.0007325428,0.00369561,0.004253109,0.00251679,0.007951305],"category_scores_gemma":[0.04428582,0.0005740457,0.0008983677,0.004596435,0.0005188072,0.003910356,0.002480269,0.00145234,0.007698848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001679608,"about_ca_system_score_gemma":0.001216615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005774445,"about_ca_topic_score_gemma":0.006376032,"domain_scores_codex":[0.9907488,0.00277075,0.001089169,0.001239008,0.003719044,0.0004332252],"domain_scores_gemma":[0.9716196,0.01434919,0.0008237833,0.004152623,0.008336349,0.0007184905],"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":[0.002622388,0.001665563,0.007363006,0.002077942,0.0004535078,0.0003194883,0.0003855438,0.04328428,0.03042448,0.004552641,0.08880453,0.8180467],"study_design_scores_gemma":[0.0006173987,0.001659449,0.005800229,0.0002346284,0.0003228938,0.0004375241,0.0004651037,0.8896874,0.06157047,0.009607523,0.02946205,0.0001354057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.3984502,0.009690199,0.3840013,0.001332371,0.002264181,0.002719776,0.01934374,0.1375375,0.04466077],"genre_scores_gemma":[0.5506876,0.001441722,0.3523034,0.0006856382,0.0004728636,0.001229921,0.06919033,0.005893182,0.01809529],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007951305,"threshold_uncertainty_score":0.03908175,"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."}}