{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003790569,0.00007837556,0.0000789624,0.00008204574,0.00007441718,0.0002262284,0.0003362237,0.00004179751,0.00002493042],"category_scores_gemma":[0.00002637268,0.00006845349,0.00006842882,0.0001567147,0.000004354801,0.0002770312,0.00004781518,0.00006142479,0.00001646893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003946647,"about_ca_system_score_gemma":0.00008112843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000024087,"about_ca_topic_score_gemma":0.0000501752,"domain_scores_codex":[0.9991877,0.00001474711,0.0001456594,0.0003156014,0.000142262,0.0001940458],"domain_scores_gemma":[0.9994441,0.00009022625,0.00001667827,0.0003801555,0.00003431406,0.000034541],"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":[0.000007356648,0.00003633629,0.0000203257,0.0001750885,0.00001819727,0.00000793026,0.003739271,0.02597504,0.00371879,0.9147447,0.00210859,0.04944838],"study_design_scores_gemma":[0.0002438851,0.000009570109,0.000003175579,0.00002896526,0.000004934467,5.680965e-7,0.00002764402,0.9903461,0.002139952,0.005161323,0.001941726,0.0000921836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004598801,0.0002402866,0.9889576,0.001881997,0.0003185024,0.0001945796,0.000004174598,0.0005454355,0.003258667],"genre_scores_gemma":[0.775692,6.862321e-7,0.2223986,0.0006271043,0.00008236126,0.00003142442,0.000007796215,0.000008452907,0.001151584],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.964371,"threshold_uncertainty_score":0.2791452,"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."}}