{"id":"W4385570798","doi":"10.18653/v1/2023.acl-long.136","title":"Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tsinghua University","keywords":"Generalization; Computer science; Scheme (mathematics); Source code; Labrador Retriever; Open source; Plug-in; Set (abstract data type); Plug and play; Code (set theory); Artificial intelligence; Operating system; Mathematics; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001551693,0.00006469459,0.00009097835,0.000166645,0.00002028071,0.00002751189,0.0002770136,0.00003755832,0.0000201294],"category_scores_gemma":[0.00001830971,0.00006111793,0.00002406512,0.0008087123,0.000007742767,0.0003844546,0.000111358,0.00003311398,0.00002204479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002921513,"about_ca_system_score_gemma":0.00004487938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005654676,"about_ca_topic_score_gemma":0.00004648338,"domain_scores_codex":[0.9991912,0.0000271045,0.000215709,0.0002193422,0.0002074097,0.0001392301],"domain_scores_gemma":[0.9995701,0.00002231992,0.00005312165,0.0002872905,0.00003889996,0.00002824663],"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":[0.000009132017,0.0000508193,0.0008169646,0.00004460988,0.00002060954,0.00002653093,0.008009991,0.4724347,0.1317705,0.3396356,0.0008883121,0.0462923],"study_design_scores_gemma":[0.0002110586,0.0000131943,0.0007935915,0.000005335565,0.000001257274,7.933174e-7,0.0001007105,0.9756438,0.01775755,0.005381943,0.00001955308,0.000071174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4098019,0.00003254337,0.5883079,0.0001845905,0.00009735523,0.000078372,5.423047e-7,0.0001202247,0.001376574],"genre_scores_gemma":[0.9550227,0.00002125385,0.04269975,0.0002082817,0.00002400606,0.000008300794,0.00001020987,0.000006526252,0.001999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5456082,"threshold_uncertainty_score":0.2492317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03114723848441501,"score_gpt":0.2720054915364587,"score_spread":0.2408582530520437,"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."}}