{"id":"W4327644059","doi":"10.1007/978-3-031-28238-6_7","title":"Improving the Generalizability of the Dense Passage Retriever Using Generated Datasets","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Overfitting; Generalizability theory; Domain (mathematical analysis); Context (archaeology); Artificial intelligence; Information retrieval; Focus (optics); Encoder; Labrador Retriever; Training set; Data mining; Pattern recognition (psychology); Mathematics; Statistics","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":[0.008357726,0.002428247,0.003026247,0.006605639,0.001213177,0.00384846,0.003347661,0.002840825,0.006595774],"category_scores_gemma":[0.04674951,0.0008399564,0.002084918,0.005525048,0.0007114903,0.006391327,0.003216221,0.002366917,0.01047498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008057522,"about_ca_system_score_gemma":0.002032737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01713517,"about_ca_topic_score_gemma":0.02014037,"domain_scores_codex":[0.9931049,0.002154335,0.0006195444,0.002234563,0.001510142,0.0003765755],"domain_scores_gemma":[0.9745285,0.01276673,0.0003603574,0.008650783,0.003366989,0.000326557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002818149,0.001205271,0.01392064,0.001666627,0.001585791,0.000895124,0.0007304747,0.05054885,0.04214343,0.003779136,0.145784,0.7349225],"study_design_scores_gemma":[0.0007301657,0.0006285735,0.01010867,0.0001269472,0.0006160715,0.0008859728,0.0007103024,0.9172959,0.02664361,0.01129518,0.03081142,0.0001472439],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3084065,0.008775915,0.4554533,0.002416098,0.001738574,0.001316998,0.04569564,0.162735,0.01346204],"genre_scores_gemma":[0.4729329,0.002288706,0.3493857,0.001216209,0.001024048,0.0007010159,0.1558175,0.006100635,0.01053314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01713517,"threshold_uncertainty_score":0.04420036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04281425477695212,"score_gpt":0.25934468536601,"score_spread":0.2165304305890579,"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."}}