{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02139088,0.002826125,0.002327372,0.0111516,0.0007572554,0.006552254,0.003480029,0.002027353,0.002833283],"category_scores_gemma":[0.1017939,0.001159776,0.001905944,0.01351684,0.001525542,0.01201968,0.00349889,0.002500621,0.001329367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003470263,"about_ca_system_score_gemma":0.00406876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01263687,"about_ca_topic_score_gemma":0.01095258,"domain_scores_codex":[0.9805744,0.009674644,0.00169193,0.001884948,0.005690064,0.0004840532],"domain_scores_gemma":[0.8621907,0.1155957,0.00310958,0.009331219,0.008551327,0.001221606],"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":[0.0003403126,0.0004427538,0.01279319,0.008273667,0.0006381223,0.00008084342,0.0007212475,0.05737884,0.001696563,0.03757945,0.02109951,0.8589554],"study_design_scores_gemma":[0.0001082051,0.001284005,0.01533799,0.009376661,0.001282369,0.0007134819,0.00227203,0.6213616,0.01013856,0.1691439,0.1686194,0.0003618324],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.06432705,0.3132653,0.5630003,0.009487691,0.0006788916,0.0009419128,0.005586789,0.01033927,0.03237273],"genre_scores_gemma":[0.2393884,0.1435863,0.5995519,0.001665721,0.0006638493,0.0007823127,0.01080291,0.00159956,0.001959101],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.02139088,"threshold_uncertainty_score":0.1131271,"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."}}