{"id":"W4404818373","doi":"10.1007/978-981-96-0579-8_20","title":"Enhancing RAG’s Retrieval via Query Backtranslations","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Information retrieval; Query expansion; Query optimization; Database","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008481041,0.0005557241,0.0004934998,0.000898107,0.0003454493,0.0009456764,0.003180921,0.0003781195,0.00004809197],"category_scores_gemma":[0.00002451634,0.0004873993,0.0001810236,0.0009052523,0.0004205072,0.001071033,0.001779776,0.001195914,0.0002715052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002534478,"about_ca_system_score_gemma":0.0005902248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002549126,"about_ca_topic_score_gemma":0.00006648303,"domain_scores_codex":[0.9956435,0.00002511675,0.0006266425,0.001868306,0.001162969,0.0006734508],"domain_scores_gemma":[0.9973084,0.0004243797,0.0001811277,0.001677165,0.0001922963,0.0002166731],"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":[0.000009148855,0.00003331384,0.000006279412,0.0001176591,0.00002484996,0.0003247171,0.001127527,0.0116351,0.002120467,0.05079139,0.00009595067,0.9337136],"study_design_scores_gemma":[0.0001434822,0.00009849101,0.00001625909,0.0008295631,0.00001361624,0.0001195522,1.104609e-7,0.694223,0.00486631,0.2913493,0.007618061,0.0007222252],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001587936,0.001840723,0.9887275,0.0008610343,0.004310724,0.0003033001,0.00001614235,0.0003351296,0.003589573],"genre_scores_gemma":[0.03476374,0.000178141,0.9578261,0.001487565,0.001874997,0.000008792755,0.00003286061,0.000105323,0.003722424],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9329914,"threshold_uncertainty_score":0.9997578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01386813357093654,"score_gpt":0.2496014352438606,"score_spread":0.2357333016729241,"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."}}