{"id":"W4376632742","doi":"10.48550/arxiv.2305.07393","title":"Prompt Learning to Mitigate Catastrophic Forgetting in Cross-lingual Transfer for Open-domain Dialogue Generation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Bridging (networking); Computer science; Forgetting; Transfer of learning; Open domain; Natural language processing; Artificial intelligence; Code (set theory); Context (archaeology); Domain (mathematical analysis); Simple (philosophy); Cognitive psychology; Set (abstract data type); Psychology; Programming language; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.004158818,0.001467603,0.0008061816,0.0006188514,0.000582307,0.001087735,0.001888676,0.001244444,0.003518427],"category_scores_gemma":[0.02073319,0.0004356864,0.0005223901,0.0005000548,0.0007766547,0.003483692,0.003347834,0.002871122,0.001980157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005404959,"about_ca_system_score_gemma":0.001091999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001185628,"about_ca_topic_score_gemma":0.002059754,"domain_scores_codex":[0.997766,0.001138532,0.0001098985,0.0006390035,0.0002112925,0.000135326],"domain_scores_gemma":[0.9915481,0.005286927,0.0002645729,0.001642215,0.0008930181,0.0003651648],"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":[0.0008467755,0.0006866248,0.006677269,0.0007515682,0.0001227661,0.0006001907,0.002248704,0.06145168,0.0785509,0.004954876,0.01127892,0.8318298],"study_design_scores_gemma":[0.0001894059,0.0008206402,0.003445768,0.00007857261,0.00008346258,0.0006123394,0.0007934587,0.8853657,0.07250092,0.02388084,0.0121241,0.0001047816],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1023405,0.0009866204,0.8654382,0.0004628955,0.0003751476,0.00024807,0.0003540707,0.02744588,0.002348672],"genre_scores_gemma":[0.7938678,0.0001924443,0.2009407,0.0004279832,0.0001045932,0.000334965,0.0009117831,0.0009755412,0.002244254],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004158818,"threshold_uncertainty_score":0.02199423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1541530916135981,"score_gpt":0.2496689618535274,"score_spread":0.09551587023992938,"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."}}