{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004032673,0.00009632943,0.0001402816,0.0001406796,0.00004814788,0.0001114362,0.000409187,0.00004035505,0.00001869262],"category_scores_gemma":[0.00009526088,0.00008324222,0.00006769666,0.0002561658,0.000006929088,0.0003262981,0.0002341299,0.0001139043,0.00001582752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002327357,"about_ca_system_score_gemma":0.00004671887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006545838,"about_ca_topic_score_gemma":0.00001753809,"domain_scores_codex":[0.9990147,0.00002595662,0.0002147174,0.0003592526,0.0001661706,0.0002192215],"domain_scores_gemma":[0.9993244,0.0001649296,0.00002645883,0.0003653671,0.00004223234,0.00007657607],"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":[0.00001993883,0.00003055651,0.00006660476,0.0004133127,0.0000526874,0.00006635834,0.02974723,0.4228037,0.04624458,0.2566049,0.002857165,0.241093],"study_design_scores_gemma":[0.0000971169,0.00006152811,0.000002108798,0.00007638352,0.00000435336,0.000004378753,0.00008662324,0.9854199,0.01079969,0.001591572,0.001752459,0.000103944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07055081,0.0001664412,0.923363,0.0009001308,0.0002002202,0.0001574506,0.00000161429,0.0003004211,0.004359853],"genre_scores_gemma":[0.8188514,0.000001325951,0.1775027,0.0001966149,0.00006816483,0.00001814259,0.000001883256,0.00001041149,0.003349371],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7483006,"threshold_uncertainty_score":0.3394519,"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."}}