{"id":"W7108322104","doi":"10.1145/3767695.3769522","title":"SIGIR-AP 2025 Tutorial on Retrieval and Ranking with LLMs (R <sup>2</sup> LLMs)","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generative grammar; Ranking (information retrieval); Field (mathematics); Software deployment; Generative model; Language model","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":[0.003767858,0.003139629,0.001597301,0.003619679,0.0009494983,0.005328378,0.003249137,0.002420106,0.08812266],"category_scores_gemma":[0.006329351,0.00109783,0.001482702,0.005316124,0.0009489842,0.006363546,0.002698984,0.003255888,0.0998706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001916354,"about_ca_system_score_gemma":0.002360574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005638012,"about_ca_topic_score_gemma":0.009439745,"domain_scores_codex":[0.9980577,0.0005109311,0.0001554805,0.0003604479,0.0007312359,0.0001842493],"domain_scores_gemma":[0.9974385,0.0009968635,0.00009248307,0.0003806047,0.0007573164,0.000334111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008215947,0.00006941877,0.0001260325,0.0005929105,0.0000576555,0.0000738156,0.00006900848,0.002854831,0.002069111,0.01079369,0.570945,0.4122664],"study_design_scores_gemma":[0.00002356576,0.0001290885,0.000448986,0.0002546265,0.0000302565,0.0004500475,0.00007453955,0.01155367,0.002078366,0.01872638,0.9661659,0.00006472113],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.003080634,0.2192264,0.5337774,0.009638846,0.02919725,0.0006928423,0.006797205,0.03227338,0.165316],"genre_scores_gemma":[0.02746635,0.1404968,0.379613,0.008066275,0.02633349,0.00101859,0.02542474,0.008300442,0.3832804],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.08812266,"threshold_uncertainty_score":0.2947997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07174231149309737,"score_gpt":0.3878560491525736,"score_spread":0.3161137376594763,"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."}}