{"id":"W4404021177","doi":"10.1007/s44163-024-00175-8","title":"A survey on augmenting knowledge graphs (KGs) with large language models (LLMs): models, evaluation metrics, benchmarks, and challenges","year":2024,"lang":"en","type":"article","venue":"Discover Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Toronto Metropolitan University","funders":"","keywords":"Computer science; Data science; Natural language processing","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002559866,0.0002715557,0.000234982,0.0004149402,0.0001765133,0.0006131414,0.0005399,0.0000901905,0.00002236596],"category_scores_gemma":[0.0001144718,0.0002264612,0.00006616025,0.0008772924,0.00005659086,0.001376423,0.000275791,0.0002655359,0.00002759468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009048446,"about_ca_system_score_gemma":0.0001707085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004064725,"about_ca_topic_score_gemma":0.002075926,"domain_scores_codex":[0.9972215,0.0002703436,0.0003967589,0.0009735085,0.000682191,0.0004556618],"domain_scores_gemma":[0.9986367,0.000390863,0.00007313325,0.0006046726,0.0001824946,0.0001120977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001515624,0.0001172793,0.00002875142,0.00006371224,0.00003930685,0.00001262905,0.009224171,0.0359299,0.00003154632,0.6805517,0.00003155771,0.2739543],"study_design_scores_gemma":[0.0000350021,0.00007662268,0.0001111371,0.0001474981,0.00002188284,0.00000250654,0.0006880139,0.8805811,0.0009707469,0.1170719,0.00003580808,0.0002578021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04945419,0.02957213,0.9165952,0.000281018,0.0005254294,0.0004145249,0.00003157735,0.000154367,0.002971588],"genre_scores_gemma":[0.995872,0.0010216,0.002834752,0.00004488463,0.00007649979,0.00004213781,0.00003392146,0.00002334146,0.00005086679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9464178,"threshold_uncertainty_score":0.923482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1556049002397965,"score_gpt":0.3427390326293876,"score_spread":0.1871341323895911,"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."}}