{"id":"W4396831993","doi":"10.1145/3613904.3641960","title":"Human-LLM Collaborative Annotation Through Effective Verification of LLM Labels","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Annotation; Leverage (statistics); Computer science; Domain (mathematical analysis); Natural language processing; Reliability (semiconductor); Artificial intelligence; Information retrieval; Data science","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":[0.0001815186,0.00007464862,0.00009829213,0.00005741206,0.00005350793,0.00009164224,0.0002224194,0.00004133801,0.00001800675],"category_scores_gemma":[0.00002444231,0.00006579985,0.00002538348,0.0005758145,0.00002572458,0.0006918698,0.000052195,0.00006480484,0.00003585062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005036829,"about_ca_system_score_gemma":0.00005824726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000558868,"about_ca_topic_score_gemma":0.000008712621,"domain_scores_codex":[0.9991997,0.00006724712,0.0001746962,0.000291409,0.0001714032,0.00009551723],"domain_scores_gemma":[0.9993973,0.00008834922,0.00004588257,0.0002795699,0.0001719962,0.00001687501],"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":[0.000001653771,0.00004908329,0.00002984573,0.00005466202,0.00002550157,0.000003069868,0.007257964,0.001169437,0.01759362,0.9483942,0.0007687415,0.02465223],"study_design_scores_gemma":[0.0005220313,0.0005680301,0.003968015,0.0001954857,0.00002607219,0.000005102956,0.0005204952,0.6802709,0.2106749,0.09639229,0.006466235,0.0003904364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05305293,0.0002771428,0.9322104,0.000508457,0.0003229739,0.000311198,0.000003771162,0.0002055654,0.01310752],"genre_scores_gemma":[0.946593,0.000006354939,0.05270426,0.00006573555,0.0000424809,0.00003675037,0.000002842216,0.000005044854,0.0005435695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.89354,"threshold_uncertainty_score":0.268324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01972640779648407,"score_gpt":0.3134079163418643,"score_spread":0.2936815085453802,"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."}}