{"id":"W4393145623","doi":"10.1609/aaai.v38i21.30433","title":"Improving Faithfulness in Abstractive Text Summarization with EDUs Using BART (Student Abstract)","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Automatic summarization; Natural language processing; Computer science; Psychology; Linguistics; Mathematics education; Artificial intelligence; Philosophy","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":[0.001213392,0.0009946589,0.0007864179,0.001279347,0.0004199281,0.00118062,0.0006722321,0.0006394156,0.002238124],"category_scores_gemma":[0.005301613,0.0002764002,0.0006061624,0.0008415602,0.0003050248,0.001985994,0.0009955444,0.001079397,0.001645837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002995387,"about_ca_system_score_gemma":0.0004841965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001361521,"about_ca_topic_score_gemma":0.002223882,"domain_scores_codex":[0.9992938,0.0002127928,0.00007222602,0.0002060063,0.000158593,0.00005661942],"domain_scores_gemma":[0.997346,0.001268346,0.0002885668,0.0003299968,0.0006537318,0.0001133956],"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":[0.0006912819,0.0001907067,0.001089898,0.0005790553,0.0001113626,0.000183765,0.0008063104,0.01990372,0.09953494,0.002161823,0.007978269,0.8667688],"study_design_scores_gemma":[0.0002423788,0.001126399,0.004876336,0.00009666575,0.0004927271,0.0002898939,0.0008457529,0.7757081,0.1823033,0.007564406,0.02634247,0.0001115789],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1532486,0.002660886,0.8229367,0.0005457529,0.0003745296,0.0002505062,0.0009916035,0.01562572,0.003365794],"genre_scores_gemma":[0.5451716,0.000764076,0.4417507,0.0002499348,0.0003485437,0.0002305901,0.004021495,0.0006816064,0.00678154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002238124,"threshold_uncertainty_score":0.007487297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06324586238832317,"score_gpt":0.3050327422802676,"score_spread":0.2417868798919444,"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."}}