{"id":"W4407244642","doi":"10.48550/arxiv.2502.03699","title":"LLM Alignment as Retriever Optimization: An Information Retrieval Perspective","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Library Science and Information Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Naval Research; Defense Advanced Research Projects Agency; Cisco Systems; National Science Foundation","keywords":"Perspective (graphical); Labrador Retriever; Information retrieval; Computer science; Medicine; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004008326,0.00103043,0.001546267,0.001622432,0.0008943852,0.002724269,0.002009765,0.00152896,0.005244045],"category_scores_gemma":[0.01440174,0.0004959891,0.0008321389,0.0024056,0.00129437,0.00471472,0.002323887,0.002185409,0.003179466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001396732,"about_ca_system_score_gemma":0.00223546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002244194,"about_ca_topic_score_gemma":0.003917999,"domain_scores_codex":[0.9960828,0.002044608,0.0002187543,0.0005738916,0.0008816336,0.0001983196],"domain_scores_gemma":[0.9956601,0.001856335,0.0004206791,0.001288574,0.0006180905,0.0001561614],"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":[0.0003162118,0.0003341956,0.002127615,0.0005741873,0.0001456063,0.0001989813,0.0004382094,0.2671088,0.01696132,0.1171425,0.01752264,0.5771297],"study_design_scores_gemma":[0.00005285574,0.0001550308,0.0004272499,0.0000352256,0.000035713,0.0001579829,0.0001049471,0.8911999,0.009773186,0.08556091,0.01245408,0.0000429692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008475552,0.0008493782,0.9836405,0.0008420396,0.00007769875,0.0001104015,0.0001354569,0.001918944,0.003950048],"genre_scores_gemma":[0.2422789,0.0007612305,0.7466506,0.0006971647,0.0002117775,0.0002628846,0.0006771574,0.0009485469,0.007511775],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005244045,"threshold_uncertainty_score":0.02119827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02837275094583898,"score_gpt":0.2715936308975445,"score_spread":0.2432208799517055,"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."}}