{"id":"W4400528870","doi":"10.1145/3626772.3657992","title":"LLM4Eval: Large Language Model for Evaluation in IR","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada); University of Waterloo","funders":"Engineering and Physical Sciences Research Council; Vrije Universiteit Amsterdam; Universiteit van Amsterdam","keywords":"Computer science; Programming language; 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":[0.05348951,0.003093614,0.002472978,0.002995404,0.001638736,0.006747421,0.00672764,0.004754776,0.02127181],"category_scores_gemma":[0.111073,0.00155947,0.003341486,0.001843337,0.00159953,0.007882156,0.008430813,0.007467748,0.00828849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003257018,"about_ca_system_score_gemma":0.00386818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006608891,"about_ca_topic_score_gemma":0.0121503,"domain_scores_codex":[0.9342828,0.05330316,0.002304941,0.003364014,0.005921588,0.0008234938],"domain_scores_gemma":[0.9314945,0.04927431,0.001263616,0.0113543,0.004877843,0.001735366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003978868,0.001340257,0.004413651,0.002729849,0.001833772,0.0004721872,0.00107863,0.08130366,0.006516882,0.02833234,0.3276747,0.5403252],"study_design_scores_gemma":[0.001291809,0.001016485,0.001817902,0.0004275115,0.0002781899,0.0002771528,0.0003560404,0.8551313,0.009861694,0.06343696,0.06586042,0.0002444588],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01719351,0.0036615,0.8489829,0.00351244,0.002255681,0.00305157,0.01071495,0.0974691,0.01315841],"genre_scores_gemma":[0.1951879,0.0007569673,0.7495722,0.002394988,0.0004343164,0.005549413,0.02776255,0.01128193,0.007059746],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05348951,"threshold_uncertainty_score":0.282883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05657543100605471,"score_gpt":0.3574910327463317,"score_spread":0.300915601740277,"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."}}