{"id":"W4221147223","doi":"10.18653/v1/2022.acl-long.359","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Swift; Inference; Language model; Computation; Code (set theory); Encoder; Set (abstract data type); Artificial intelligence; Sequence (biology); Architecture; Energy (signal processing); Computer engineering; Machine learning; Theoretical computer science; Programming language; Operating system","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":[0.001659487,0.001531084,0.0009943703,0.0007923522,0.0005660667,0.001658401,0.002671176,0.001159212,0.006691596],"category_scores_gemma":[0.005857359,0.001117626,0.001222118,0.0006064143,0.0008327049,0.004805635,0.002884312,0.003043647,0.003399521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008416774,"about_ca_system_score_gemma":0.001645457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005619434,"about_ca_topic_score_gemma":0.01609197,"domain_scores_codex":[0.9990081,0.0002751177,0.00004856399,0.000268511,0.0002810195,0.0001186037],"domain_scores_gemma":[0.9982681,0.0007220227,0.00009238564,0.0005931875,0.0002368237,0.00008746171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007081508,0.000339954,0.00276269,0.0002457006,0.0002618354,0.0004580556,0.0003631604,0.380598,0.02032077,0.04287367,0.02387752,0.5271904],"study_design_scores_gemma":[0.00002421677,0.00002872979,0.0001081004,0.00000748452,0.00001502769,0.00003556235,0.000023229,0.9738341,0.005014976,0.01872423,0.002170093,0.00001421917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01614218,0.0002036997,0.9633664,0.0002696401,0.00008907574,0.0000606321,0.0004939148,0.01669285,0.002681524],"genre_scores_gemma":[0.3616567,0.0002489855,0.6214909,0.0005479056,0.0001207985,0.0001918278,0.003968866,0.003301196,0.008472863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006691596,"threshold_uncertainty_score":0.02238566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01135981089682939,"score_gpt":0.2152195700374592,"score_spread":0.2038597591406298,"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."}}