{"id":"W4396819963","doi":"10.1145/3626772.3657864","title":"Ranked List Truncation for Large Language Model-based Re-Ranking","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"HORIZON EUROPE Framework Programme; China Scholarship Council; European Commission; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Baidu","keywords":"Computer science; Ranking (information retrieval); Truncation (statistics); Information retrieval; Natural language processing; Machine learning","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":[0.006233093,0.002046433,0.002937307,0.002872394,0.001354634,0.002873785,0.003236252,0.001911896,0.006291174],"category_scores_gemma":[0.02691765,0.000735982,0.001771573,0.003131363,0.001429119,0.005557876,0.002587528,0.002736319,0.005663395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001715147,"about_ca_system_score_gemma":0.002893907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006091006,"about_ca_topic_score_gemma":0.01278832,"domain_scores_codex":[0.9942521,0.002620071,0.0004125069,0.0008320301,0.001450756,0.000432533],"domain_scores_gemma":[0.9818747,0.009655662,0.001177045,0.004556003,0.002231497,0.0005051197],"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":[0.0007691171,0.0006426242,0.003871964,0.001236455,0.0003549559,0.0003580578,0.0006741644,0.2279345,0.0155296,0.03474597,0.04158789,0.6722947],"study_design_scores_gemma":[0.00009997399,0.0003327204,0.0006817782,0.00005604338,0.0001019617,0.0002537764,0.0001368408,0.9466748,0.007788318,0.03412461,0.009669571,0.0000795566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02808238,0.003871239,0.9526033,0.0008830483,0.0003247921,0.0004140744,0.0009254761,0.008537835,0.004357724],"genre_scores_gemma":[0.3445683,0.00134556,0.6342457,0.0008997721,0.0006535103,0.000559243,0.003556055,0.001834183,0.01233766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006291174,"threshold_uncertainty_score":0.03296417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02541699024241924,"score_gpt":0.2931228242981274,"score_spread":0.2677058340557081,"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."}}