{"id":"W7126374618","doi":"10.18653/v1/2024.law-1.10","title":"Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation","year":2024,"lang":"","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Active learning (machine learning); Annotation; Focus (optics); Identification (biology)","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000472597,0.0003229572,0.0002641182,0.0002066238,0.0009398464,0.001555359,0.0003003302,0.0001644409,0.000268132],"category_scores_gemma":[0.00009825085,0.000308867,0.00009346258,0.0007908471,0.0001282902,0.001629995,0.0002551385,0.001037023,0.0002960314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001120787,"about_ca_system_score_gemma":0.0001203218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000302321,"about_ca_topic_score_gemma":0.00003575708,"domain_scores_codex":[0.9972262,0.0003631782,0.0004593208,0.001108169,0.0004056103,0.0004375625],"domain_scores_gemma":[0.9990146,0.0002980791,0.0001668932,0.0002759164,0.0001283118,0.0001162718],"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":[0.000006728511,0.00009056665,0.0006126338,0.0002609516,0.00009458953,0.00002706628,0.02978958,0.0007664662,0.03184267,0.1594266,0.0001862917,0.7768959],"study_design_scores_gemma":[0.0002373209,0.0004695491,0.006965454,0.0004305076,0.00004397229,0.00003252922,0.00177648,0.9641201,0.003886486,0.002071406,0.01951134,0.0004548662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06915915,0.0009764145,0.8988734,0.002695369,0.000999469,0.000272353,0.000002030259,0.0006620025,0.02635979],"genre_scores_gemma":[0.9681488,0.0001791316,0.01873538,0.00009363329,0.0004797642,0.00001599611,0.00001762398,0.00003264114,0.01229704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9633536,"threshold_uncertainty_score":0.9999363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02140823191819688,"score_gpt":0.3204418519509792,"score_spread":0.2990336200327823,"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."}}