{"id":"W4408146816","doi":"10.1109/icairc64177.2024.10900179","title":"Comparative Analysis of Listwise Reranking with Large Language Models in Limited-Resource Language Contexts","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Resource (disambiguation); Natural language processing; Language model; 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":[],"consensus_categories":[],"category_scores_codex":[0.000336571,0.0001340032,0.0003757065,0.000582075,0.0000261352,0.00011426,0.0004506411,0.00004472109,0.00003610197],"category_scores_gemma":[0.000007697533,0.000102205,0.00009080897,0.001768623,0.00002294643,0.0003895351,0.0001497664,0.000162299,0.000005484614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004003779,"about_ca_system_score_gemma":0.00003989772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006363653,"about_ca_topic_score_gemma":0.001758193,"domain_scores_codex":[0.9987099,0.0000786012,0.000274671,0.0004173807,0.0002767413,0.0002426617],"domain_scores_gemma":[0.9991779,0.0001637371,0.00004988708,0.0005216265,0.00003685665,0.00004997717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000408144,0.0002251781,0.002035475,0.0001287877,0.001160253,0.0005725719,0.3435,0.3163911,0.003269821,0.3165047,0.000251659,0.01591967],"study_design_scores_gemma":[0.0002266049,0.00002333308,0.0004246441,0.00008936233,0.00007140784,0.000002700028,0.001637653,0.9959932,0.001103875,0.0001588417,0.0001343687,0.0001340263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4011972,0.001300506,0.5890539,0.0001448764,0.0000193048,0.00009638198,0.000007503221,0.0001423127,0.008038009],"genre_scores_gemma":[0.9853289,0.000002889895,0.01371431,0.0002344898,0.00001609529,0.000007543275,0.000009446287,0.000006298835,0.0006800357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6796021,"threshold_uncertainty_score":0.4167798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02163557701518332,"score_gpt":0.2885934192222355,"score_spread":0.2669578422070522,"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."}}