{"id":"W4368755400","doi":"10.48550/arxiv.2305.02156","title":"Zero-Shot Listwise Document Reranking with a Large Language Model","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Pointwise; Ranking (information retrieval); Relevance (law); Information retrieval; Encoder; Pointwise mutual information; Task (project management); Natural language processing; Zero (linguistics); Language model; Identifier; Artificial intelligence; Mathematics; Mutual information; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002719708,0.000337883,0.0003087277,0.0004171588,0.0001974835,0.0002887494,0.00241571,0.0002718538,0.00001770911],"category_scores_gemma":[0.00002729572,0.0003340349,0.0001414656,0.0007593406,0.00009470701,0.000514687,0.002771754,0.0005549284,0.0001610689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002377867,"about_ca_system_score_gemma":0.00018534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009166445,"about_ca_topic_score_gemma":0.00008196499,"domain_scores_codex":[0.9978796,0.00005739363,0.0002007398,0.001225504,0.000171971,0.0004648225],"domain_scores_gemma":[0.9975194,0.00006381717,0.0002676307,0.001942941,0.000100586,0.0001055845],"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":[0.0000303997,0.00009359215,0.0008754882,0.00008095171,0.0001007116,0.0004676621,0.001181857,0.1495141,0.00008767081,0.8453997,0.001483341,0.0006845027],"study_design_scores_gemma":[0.0008350962,0.0000643144,0.0003682974,0.0001766468,0.00006611396,0.000003596574,0.0004762569,0.8257931,0.0005449471,0.1701232,0.0008139885,0.0007344678],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09628405,0.00006058993,0.8983411,0.0006913357,0.0002012257,0.0003391783,0.00001952341,0.002278968,0.00178406],"genre_scores_gemma":[0.9823565,0.0001779895,0.006363506,0.0001018177,0.00002021691,0.000006337376,0.00002907562,0.00002811301,0.01091639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8919775,"threshold_uncertainty_score":0.9999112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09702878345608794,"score_gpt":0.2197408233135964,"score_spread":0.1227120398575085,"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."}}