{"id":"W4402927277","doi":"10.23977/acss.2024.080608","title":"Application of RAG Model Based on Retrieval Enhanced Generation Technique in Complex Query Processing","year":2024,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Cognitive Computing and Networks","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Query optimization; Information retrieval; Query expansion; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"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":[0.002059538,0.0007922782,0.001015576,0.001323045,0.0006824216,0.00197026,0.001936065,0.001459869,0.005550912],"category_scores_gemma":[0.004666626,0.0002949709,0.001119332,0.00131131,0.001273149,0.003783902,0.0012413,0.00131704,0.00141196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028197,"about_ca_system_score_gemma":0.001357774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00499521,"about_ca_topic_score_gemma":0.002651804,"domain_scores_codex":[0.9984547,0.0005390264,0.00008642617,0.0003174486,0.0004245696,0.0001779104],"domain_scores_gemma":[0.9979286,0.001165844,0.0001523057,0.0003489679,0.0003178519,0.00008637496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009363529,0.0004209281,0.003424227,0.0004776812,0.0001824669,0.00113245,0.001114832,0.4985102,0.03730394,0.2048153,0.01251455,0.2391672],"study_design_scores_gemma":[0.00003503813,0.0001279385,0.0002294011,0.00001138545,0.00003207186,0.0002168799,0.00005306867,0.967747,0.003102474,0.02507706,0.003338163,0.00002954911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02670233,0.001225495,0.9610813,0.000905139,0.0001192589,0.0002309536,0.0002234572,0.002204449,0.007307662],"genre_scores_gemma":[0.6850646,0.00109141,0.3041284,0.0005660633,0.0001789865,0.0003269902,0.0004926978,0.0003264683,0.007824443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005550912,"threshold_uncertainty_score":0.01856971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02747697177754051,"score_gpt":0.2992218555801802,"score_spread":0.2717448838026397,"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."}}