{"id":"W4402684133","doi":"10.18653/v1/2024.findings-acl.85","title":"RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alliance de recherche numérique du Canada; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Shot (pellet); Computer science; Language model; Artificial intelligence; One shot; Natural language processing; Programming language; Computer graphics (images); Mechanical engineering; Engineering; Materials science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002022245,0.002685455,0.001243174,0.00107639,0.0006325467,0.001157055,0.003366985,0.002298373,0.00475127],"category_scores_gemma":[0.01024855,0.0007537212,0.00120113,0.000677403,0.0006225351,0.003066928,0.001595926,0.00370185,0.00520006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008170358,"about_ca_system_score_gemma":0.0009816347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003485958,"about_ca_topic_score_gemma":0.007387788,"domain_scores_codex":[0.9989723,0.0002952974,0.00004744287,0.0004812585,0.0001085999,0.00009520756],"domain_scores_gemma":[0.9969248,0.001858066,0.0001800933,0.0005640137,0.0003339536,0.0001390694],"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":[0.0005246463,0.0005277321,0.001963137,0.0007432772,0.0002238361,0.0003701777,0.0004822273,0.1135275,0.04718764,0.002601148,0.02217761,0.809671],"study_design_scores_gemma":[0.00006673726,0.0003019041,0.0006824197,0.00004886711,0.00005184295,0.0002159697,0.0001122573,0.9654518,0.02260885,0.006250121,0.004159708,0.00004947144],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05551965,0.001908609,0.8994278,0.0003707015,0.0002922264,0.0004026133,0.001506815,0.03771743,0.002854168],"genre_scores_gemma":[0.3899243,0.0006173547,0.5907347,0.000804037,0.0002268885,0.0009991413,0.006739812,0.002309886,0.007644024],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00475127,"threshold_uncertainty_score":0.01589459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04448948231424926,"score_gpt":0.3024851167530286,"score_spread":0.2579956344387793,"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."}}