{"id":"W4416716931","doi":"10.1016/j.knosys.2025.114980","title":"Utilizing large language models for integrating document-level contextual semantic into pseudo-relevance feedback","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Hubei Provincial Department of Education; Ontario Research Foundation","keywords":"Consistency (knowledge bases); Query expansion; Semantic matching; Matching (statistics); Relevance (law); Query language; Key (lock); Semantic heterogeneity; Probabilistic logic; Relevance feedback","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001392873,0.0002902295,0.000423142,0.0003512994,0.0004691019,0.0005696653,0.001004668,0.0001411897,0.000007290828],"category_scores_gemma":[0.0002772525,0.0002498868,0.0001889748,0.0007781467,0.00005368715,0.0009260188,0.0002111335,0.0002533268,0.0001236969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000271233,"about_ca_system_score_gemma":0.000492133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001688539,"about_ca_topic_score_gemma":0.0001867938,"domain_scores_codex":[0.9976255,0.000181876,0.0007486958,0.0004622591,0.0003555939,0.0006260991],"domain_scores_gemma":[0.9978076,0.000572636,0.0001957594,0.0006416552,0.0006448664,0.0001374726],"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":[0.0001251654,0.0004049193,0.0004084057,0.003282904,0.0001155091,0.00001611398,0.02319537,0.001506535,0.007716672,0.8868986,0.007698316,0.06863152],"study_design_scores_gemma":[0.002015357,0.00009985019,0.00004471622,0.0008443675,0.0000190847,0.000003210694,0.003440562,0.9802309,0.006148663,0.000745005,0.006076732,0.000331547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01929123,0.001206654,0.9712584,0.0002115416,0.001498367,0.001206155,0.00004054537,0.0003072225,0.004979906],"genre_scores_gemma":[0.9847729,0.00000353053,0.009603936,0.0002010548,0.00009493752,0.0002848041,0.00003376673,0.00001688294,0.004988223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9787244,"threshold_uncertainty_score":0.9999954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03351359701544305,"score_gpt":0.3182647216926604,"score_spread":0.2847511246772174,"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."}}