{"id":"W4409299747","doi":"10.1016/j.mlwa.2025.100649","title":"Optimizing translation for low-resource languages: Efficient fine-tuning with custom prompt engineering in large language models","year":2025,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact","funders":"University of Pretoria","keywords":"Computer science; Translation (biology); Resource (disambiguation); Chemistry","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":[0.002253906,0.002146496,0.001189509,0.0006500605,0.000574099,0.001443007,0.001786793,0.001426648,0.003437036],"category_scores_gemma":[0.009686245,0.00075667,0.001345697,0.0007285071,0.0006565089,0.003021383,0.001680523,0.003303695,0.003533306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007579121,"about_ca_system_score_gemma":0.001849217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005731475,"about_ca_topic_score_gemma":0.01189892,"domain_scores_codex":[0.9988111,0.0004941237,0.00007903234,0.0003704774,0.0001406975,0.0001044528],"domain_scores_gemma":[0.9976522,0.001483002,0.00009425441,0.0003590799,0.0003110602,0.0001003003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006374363,0.0004539703,0.004980737,0.0004939924,0.0002910738,0.0004362433,0.0005211353,0.5230421,0.02474707,0.004011263,0.01790697,0.422478],"study_design_scores_gemma":[0.00007025139,0.000118696,0.0003286225,0.00002175405,0.00005978978,0.00008409579,0.0001017714,0.9847898,0.006273767,0.004115692,0.004009444,0.00002627517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1170987,0.001925763,0.8226693,0.0009380328,0.0005334026,0.0003841918,0.001019815,0.05088485,0.004545831],"genre_scores_gemma":[0.5996606,0.0006179714,0.384933,0.001343503,0.0001860178,0.0007225327,0.004271935,0.003041567,0.005222808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005731475,"threshold_uncertainty_score":0.01191992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005241564749280432,"score_gpt":0.2498799504021441,"score_spread":0.2446383856528637,"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."}}