{"id":"W4393156816","doi":"10.1609/aaai.v38i17.29892","title":"ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; Southeast University; National Natural Science Foundation of China; National Science Foundation","keywords":"Consistency (knowledge bases); Context (archaeology); Ontology; Computer science; Political science; History; Epistemology; Artificial intelligence; Philosophy","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":[0.001764037,0.001519858,0.001079506,0.001104627,0.0005897825,0.001219185,0.003154769,0.001367459,0.007103784],"category_scores_gemma":[0.006685843,0.00069174,0.00127101,0.000602398,0.0009748733,0.005196963,0.004344248,0.002042907,0.004528595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005404769,"about_ca_system_score_gemma":0.000965084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002107204,"about_ca_topic_score_gemma":0.004789222,"domain_scores_codex":[0.9989449,0.0002636826,0.00008147219,0.0004125531,0.0002212539,0.00007609709],"domain_scores_gemma":[0.9979848,0.0008373936,0.0001511424,0.000554073,0.0003274079,0.0001452369],"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":[0.0006604625,0.0003997188,0.002336753,0.001197355,0.0001596444,0.001270827,0.001556236,0.03743096,0.1216446,0.02562154,0.0282495,0.7794723],"study_design_scores_gemma":[0.00007580629,0.0004435487,0.001709315,0.0001054587,0.0001296828,0.0009362841,0.0004947939,0.8377792,0.08621502,0.03483663,0.03711686,0.0001573838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01390288,0.0004105146,0.9577757,0.0001970174,0.00006651447,0.0002188251,0.0006230554,0.02472914,0.002076447],"genre_scores_gemma":[0.183588,0.0003970315,0.8017539,0.0003980258,0.00006493958,0.0004584782,0.004510461,0.001551268,0.007277912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007103784,"threshold_uncertainty_score":0.02376449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06822964360212178,"score_gpt":0.2939055312923517,"score_spread":0.2256758876902299,"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."}}