{"id":"W4396843976","doi":"10.1145/3589335.3641299","title":"Information Retrieval Meets Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Natural language processing; Artificial intelligence; Data science","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":[0.0002146191,0.00004853412,0.00004348486,0.00007576281,0.00002885,0.0002726591,0.0002737914,0.00003155221,0.00003721986],"category_scores_gemma":[0.00001107057,0.00003956445,0.00002634286,0.0001870217,0.000002827789,0.002304867,0.0001378557,0.00006645472,0.000262822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002190313,"about_ca_system_score_gemma":0.0000342161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000164255,"about_ca_topic_score_gemma":0.000002500402,"domain_scores_codex":[0.9994686,0.000009370458,0.0001183121,0.00009173238,0.000176732,0.0001352896],"domain_scores_gemma":[0.9996645,0.00001846981,0.000009709471,0.0002534217,0.00002014176,0.00003371185],"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":[5.97457e-7,0.000003131373,0.000001283013,0.00001776183,0.000003829529,0.000005417114,0.004714658,0.001045642,0.0000982112,0.9673955,0.001249112,0.02546486],"study_design_scores_gemma":[0.00005025168,0.000005266258,0.000004079616,0.000009671179,9.825677e-7,0.000005376208,0.00008013516,0.9811158,0.0006328397,0.006795402,0.01124493,0.00005525193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005904544,0.0002013911,0.9556491,0.001138698,0.0003492841,0.00005015857,0.000001518174,0.0005232432,0.03618202],"genre_scores_gemma":[0.9639341,0.000005192932,0.0345276,0.0005205309,0.00004635004,0.000001244631,0.000002715473,0.000002363863,0.0009598723],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9800702,"threshold_uncertainty_score":0.3378133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01474873763722081,"score_gpt":0.2531784605361799,"score_spread":0.2384297228989591,"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."}}