{"id":"W4404781191","doi":"10.18653/v1/2024.findings-emnlp.677","title":"A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers","year":2024,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","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; Alberta Innovates; DeepMind; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Automatic summarization; Decoding methods; Computer science; Algorithm; List decoding; Directed acyclic graph; Transformer; Artificial intelligence; Concatenated error correction code; Block code; Voltage; Engineering; Electrical engineering","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":[0.0009106915,0.001257316,0.0009906844,0.002796336,0.0006910418,0.001015128,0.001244195,0.001047394,0.003723045],"category_scores_gemma":[0.005550222,0.0003917982,0.0007717913,0.002746186,0.0006501758,0.001973573,0.00106074,0.001540218,0.002731641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007713296,"about_ca_system_score_gemma":0.001840105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00336211,"about_ca_topic_score_gemma":0.00515317,"domain_scores_codex":[0.9990932,0.0002078794,0.0001094363,0.0002525136,0.0002667306,0.00007016771],"domain_scores_gemma":[0.9978835,0.0009583147,0.0001549832,0.0002891546,0.000644206,0.00006989412],"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":[0.0002699487,0.00008426907,0.0006554816,0.0002625062,0.00005685179,0.000203479,0.0002215448,0.05414842,0.02787192,0.02117633,0.01595702,0.8790923],"study_design_scores_gemma":[0.0001054013,0.0002015378,0.0004503275,0.00004577588,0.00007291868,0.000401187,0.0001393297,0.9013166,0.03232374,0.04905404,0.0158313,0.00005786364],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005103697,0.000311901,0.9899524,0.0001379293,0.00006713752,0.00009541546,0.0005660001,0.002912287,0.0008533063],"genre_scores_gemma":[0.1030591,0.0004670554,0.8862307,0.0002152985,0.0001285374,0.0002279981,0.004294905,0.0006443472,0.004732063],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003723045,"threshold_uncertainty_score":0.01245487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01083618685990792,"score_gpt":0.2540388349982392,"score_spread":0.2432026481383313,"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."}}