{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003253171,0.0001636725,0.0002715485,0.00008241607,0.0001858868,0.0001877454,0.0008373649,0.00007320174,0.000008348644],"category_scores_gemma":[0.0003806134,0.00008678469,0.00008212647,0.0003410864,0.001338306,0.0002565779,0.0001559511,0.0001714775,0.000002637428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001586067,"about_ca_system_score_gemma":0.0002740505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000120857,"about_ca_topic_score_gemma":0.0002213939,"domain_scores_codex":[0.9988376,0.0000168335,0.0003600414,0.0003634892,0.0002126509,0.0002094005],"domain_scores_gemma":[0.9984606,0.0004763734,0.000198667,0.0002036618,0.0006225205,0.00003816687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004358471,0.00002508222,0.0001660742,0.00005540736,0.00003921337,3.797117e-7,0.001940584,0.000002812866,0.005537812,0.8736797,0.0001001745,0.1184092],"study_design_scores_gemma":[0.00009774194,0.0009534793,0.001742503,0.0005332764,0.0001171871,0.00008915146,0.01156719,0.04602867,0.474224,0.4636662,0.0006415863,0.0003390436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7367114,0.00112735,0.18313,0.05608045,0.001078558,0.001895319,0.00003906868,0.000212164,0.01972568],"genre_scores_gemma":[0.9953927,0.00003763791,0.00420554,0.0001826823,0.00002347537,0.00004980995,2.156485e-7,0.000006116285,0.0001017832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4686862,"threshold_uncertainty_score":0.4931044,"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."}}