{"id":"W4412886925","doi":"10.18653/v1/2025.acl-industry.56","title":"Enriching children’s stories with LLMs: Delivering multilingual data enrichment for children’s books at scale and across markets","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada)","funders":"","keywords":"Scale (ratio); Computer science; Data science; Geography; Cartography","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":[0.002264791,0.0007395712,0.0004280801,0.001529743,0.000921668,0.003116863,0.001350187,0.0007683135,0.01153771],"category_scores_gemma":[0.01380739,0.0004180814,0.0005659361,0.001250776,0.001131057,0.005613395,0.006217894,0.001415866,0.004280997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000842572,"about_ca_system_score_gemma":0.001225982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002836978,"about_ca_topic_score_gemma":0.00905707,"domain_scores_codex":[0.998486,0.0005931422,0.00006493982,0.0003292052,0.0004359994,0.00009072453],"domain_scores_gemma":[0.9920661,0.005029222,0.0002627697,0.00141111,0.0007964946,0.0004342644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009059735,0.0005020946,0.01815048,0.001980538,0.0001442967,0.00146708,0.02344073,0.006194616,0.09381591,0.02027427,0.03079621,0.8023279],"study_design_scores_gemma":[0.0002238487,0.0006268054,0.02753631,0.0005506517,0.0002281753,0.001741867,0.0170079,0.0821497,0.231235,0.05459685,0.5837544,0.0003485944],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1736476,0.001056083,0.7201856,0.002189782,0.0001484764,0.0009345628,0.005831598,0.04252461,0.05348155],"genre_scores_gemma":[0.3628719,0.0004622109,0.6099271,0.0006485782,0.0000546711,0.0007017054,0.00527556,0.003759271,0.01629904],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01153771,"threshold_uncertainty_score":0.03859746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01135112746751912,"score_gpt":0.2958524022356139,"score_spread":0.2845012747680948,"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."}}