{"id":"W4396531244","doi":"10.22215/etd/2024-15938","title":"The Fusion of Multilingual Semantic Search and Large Language Models: A New Paradigm for Enhanced Topic Exploration and Contextual Search","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Semantic search; Linguistics; Semantic Web","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":[0.0004545841,0.0001946051,0.0002949708,0.0001829663,0.0001690518,0.0002052437,0.0003536605,0.0001418443,0.000003238576],"category_scores_gemma":[0.00005381131,0.0001388289,0.00007803309,0.0002308788,0.00003603871,0.0004448879,0.0001522428,0.0002152415,0.000001718575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002458784,"about_ca_system_score_gemma":0.0001403286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002235221,"about_ca_topic_score_gemma":0.002843504,"domain_scores_codex":[0.9985297,0.00005832234,0.0003301571,0.0005031061,0.0003229391,0.0002557151],"domain_scores_gemma":[0.9990368,0.0002968364,0.00007466743,0.0003778755,0.0001449301,0.00006882579],"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":[0.0001286333,0.00006162569,0.000003590121,0.0007111515,0.0001351006,0.00000658956,0.07651023,0.0001116,0.03010414,0.2011385,0.0001916839,0.6908972],"study_design_scores_gemma":[0.0005903521,0.0002456309,0.00002522741,0.0002834654,0.00006847663,0.000002402567,0.01171252,0.7202378,0.2030983,0.06320684,0.0002046413,0.0003244065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1418168,0.003249603,0.8534564,0.0002191578,0.00008017543,0.0007084999,0.0000054149,0.0001355951,0.0003283293],"genre_scores_gemma":[0.9656189,0.001257797,0.020954,0.00002275042,0.00006224812,0.00006995095,0.0001058482,0.00002458212,0.01188391],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8325024,"threshold_uncertainty_score":0.5661279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03589096521382491,"score_gpt":0.3618835984187028,"score_spread":0.3259926332048779,"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."}}