{"id":"W4387171785","doi":"10.3233/faia230385","title":"Diversified Prior Knowledge Enhanced General Language Model for Biomedical Information Retrieval","year":2023,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ranking (information retrieval); Language model; Domain (mathematical analysis); Information retrieval; Query expansion; Domain knowledge; Artificial intelligence; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002511115,0.0001908728,0.0002475311,0.000369719,0.0001707359,0.0001125499,0.0005748409,0.0002687282,0.000004871323],"category_scores_gemma":[0.00003564185,0.0002068652,0.00007952155,0.0001676003,0.0001158876,0.0002956283,0.0002118814,0.0002287943,0.00007629249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008880183,"about_ca_system_score_gemma":0.0001368946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000556395,"about_ca_topic_score_gemma":0.00001803719,"domain_scores_codex":[0.9986301,0.000007369159,0.0005215871,0.0004130857,0.0001860743,0.0002417507],"domain_scores_gemma":[0.9991779,0.00006125351,0.0001497979,0.0004128257,0.0001014276,0.00009683969],"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":[0.00001147712,0.00001544324,3.294774e-7,0.00003928813,0.0000117972,3.616626e-7,0.002032075,0.0008443721,0.00007576337,0.5400904,0.0007290888,0.4561495],"study_design_scores_gemma":[0.00003221532,0.00001610969,3.855309e-7,0.00003222223,0.00001105077,3.603849e-7,0.0001489605,0.7379894,0.0004500046,0.2533983,0.007735759,0.0001852342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003051944,0.0001570469,0.9908717,0.0002415278,0.000450613,0.0008825853,0.00006455785,0.0001327444,0.007168711],"genre_scores_gemma":[0.02744234,0.001597923,0.7643123,0.0005563246,0.001745753,0.001140153,0.0008932808,0.0001187889,0.2021931],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.737145,"threshold_uncertainty_score":0.8435719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05235715267539773,"score_gpt":0.2965038460991165,"score_spread":0.2441466934237187,"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."}}