{"id":"W4409156994","doi":"10.1109/ieeeconf60004.2024.10942686","title":"Parameter Efficient Fine-tuning of Transformer-Based Language Models Using Dataset Pruning","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Transformer; Language model; Pruning; Artificial intelligence; Engineering; Voltage; Electrical engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001247991,0.001453088,0.001524261,0.001054002,0.0004596285,0.001413306,0.002589494,0.0008791902,0.003390898],"category_scores_gemma":[0.007645516,0.0006799456,0.001469879,0.0009542719,0.0004579594,0.002799767,0.001657347,0.001779552,0.002096657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008603192,"about_ca_system_score_gemma":0.001550705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008601866,"about_ca_topic_score_gemma":0.01581124,"domain_scores_codex":[0.9987993,0.0002831217,0.0001241218,0.0003846781,0.0002852361,0.0001235019],"domain_scores_gemma":[0.9975968,0.001028316,0.0001109807,0.0007933553,0.0003973207,0.00007320503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007876273,0.0004725597,0.004485643,0.0003412365,0.0002625262,0.000455343,0.0003011281,0.2301213,0.05679281,0.0032365,0.01732187,0.6854214],"study_design_scores_gemma":[0.00008269153,0.0001158806,0.0008620354,0.00001827585,0.00006305851,0.0001578302,0.00008480086,0.9712645,0.01833412,0.004177995,0.004802503,0.00003621702],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1091952,0.001293986,0.8373753,0.0003124684,0.0002876237,0.0003904231,0.001506616,0.04488903,0.00474939],"genre_scores_gemma":[0.5884806,0.0004746332,0.3956313,0.0007270805,0.00008476875,0.0006155092,0.007259883,0.002392472,0.004333753],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008601866,"threshold_uncertainty_score":0.01710361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03317615549535152,"score_gpt":0.3133406116317856,"score_spread":0.2801644561364341,"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."}}