{"id":"W4411120475","doi":"10.18653/v1/2025.findings-naacl.238","title":"Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs","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":"","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Context (archaeology); Machine translation; Translation (biology); Artificial intelligence; Machine learning; Natural language processing; History; Chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001839086,0.001439598,0.001460501,0.001415818,0.0009133936,0.001224756,0.001985379,0.00151809,0.002333281],"category_scores_gemma":[0.01116043,0.000607686,0.001326506,0.001438438,0.0008647158,0.002761589,0.002276382,0.001882734,0.003122605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005185787,"about_ca_system_score_gemma":0.001278439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001858022,"about_ca_topic_score_gemma":0.005236685,"domain_scores_codex":[0.9978829,0.0009508184,0.0001951959,0.0005573343,0.000319313,0.00009446836],"domain_scores_gemma":[0.9954674,0.002396421,0.0002768485,0.001030327,0.0007328319,0.00009616578],"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":[0.0006105434,0.0004187197,0.006413708,0.0006558733,0.0002224336,0.0005580744,0.0007582172,0.09864751,0.03049246,0.006883996,0.0203387,0.8339998],"study_design_scores_gemma":[0.000107967,0.0001315697,0.0009170962,0.00005730249,0.00005808233,0.0003180239,0.0002222166,0.9497977,0.02147661,0.01848713,0.008389148,0.00003707823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06631993,0.001204821,0.9095337,0.0005749934,0.0001655271,0.000235395,0.001229766,0.01839332,0.002342668],"genre_scores_gemma":[0.3311787,0.0002700228,0.6561981,0.000629255,0.0001348492,0.0005540862,0.007686356,0.001088935,0.002259684],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002333281,"threshold_uncertainty_score":0.009726107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01036603459970873,"score_gpt":0.2654209305770273,"score_spread":0.2550548959773185,"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."}}