{"id":"W4400526908","doi":"10.1145/3626772.3657707","title":"Large Language Models can Accurately Predict Searcher Preferences","year":2024,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing","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":[0.0003200866,0.00008944723,0.00009702956,0.0001116533,0.00005828142,0.0005570957,0.0007358876,0.00003676765,0.0001718715],"category_scores_gemma":[0.00001613957,0.00006214538,0.00005345224,0.0004843915,0.00001596071,0.0006751104,0.0002786712,0.0001256169,0.0001490013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001470814,"about_ca_system_score_gemma":0.0001103241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002994609,"about_ca_topic_score_gemma":0.0002151692,"domain_scores_codex":[0.9989731,0.0000482016,0.0001119961,0.0003593554,0.0002504937,0.0002568678],"domain_scores_gemma":[0.999397,0.00006265953,0.00001142321,0.0004175103,0.00002476688,0.00008661122],"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":[0.000004872898,0.0001839457,0.0008012776,0.0001751506,0.000476976,0.0004065568,0.03597824,0.001111217,0.00103047,0.5122191,0.1050792,0.3425329],"study_design_scores_gemma":[0.00005705704,0.00002488441,0.00008969205,0.00003233201,0.00001164063,0.000004743139,0.0005865586,0.9905349,0.0006388277,0.003013474,0.004879319,0.000126542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08019068,0.0009876853,0.8654788,0.002003569,0.0002196636,0.00007495302,0.0001114178,0.001083644,0.04984966],"genre_scores_gemma":[0.9854001,0.00002749171,0.005386545,0.0001538262,0.00006259403,0.000007306237,0.00002438249,0.000005658602,0.008932074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9894237,"threshold_uncertainty_score":0.5372086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07561307685075239,"score_gpt":0.3207369305742917,"score_spread":0.2451238537235393,"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."}}