{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003934912,0.00122099,0.0008440518,0.001728744,0.0004904509,0.00191518,0.0007727705,0.001317441,0.003329099],"category_scores_gemma":[0.02667455,0.0005143131,0.0007492597,0.001332811,0.0004580048,0.004940157,0.00102574,0.002296686,0.004614863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008836073,"about_ca_system_score_gemma":0.0007891445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005657483,"about_ca_topic_score_gemma":0.01307887,"domain_scores_codex":[0.9978168,0.001094382,0.0001442722,0.0004569629,0.0003480228,0.0001394765],"domain_scores_gemma":[0.9803209,0.01579235,0.0008369018,0.001515101,0.001208756,0.0003260803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00263177,0.0009692283,0.08887585,0.0008766433,0.0005902198,0.000403602,0.001548365,0.3749354,0.02694152,0.007963168,0.03530994,0.4589544],"study_design_scores_gemma":[0.00004752091,0.0001381541,0.00596815,0.00003904447,0.00004569588,0.0001073102,0.0001606759,0.9790316,0.003095741,0.009054905,0.00226655,0.00004465734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5408095,0.003284117,0.4238415,0.002813431,0.0002250518,0.0003269006,0.005663665,0.0104756,0.01256028],"genre_scores_gemma":[0.9461505,0.0003771155,0.04470861,0.0003633359,0.0001035013,0.0001645968,0.004041461,0.0004485297,0.003642329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005657483,"threshold_uncertainty_score":0.02081001,"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."}}