{"id":"W4412889244","doi":"10.18653/v1/2025.bea-1.38","title":"LLMs in alliance with Edit-based models: advancing In-Context Learning for Grammatical Error Correction by Specific Example Selection","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Selection (genetic algorithm); Computer science; Context (archaeology); Alliance; Artificial intelligence; Natural language processing; Machine learning; Political science; History","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":[0.002313992,0.001119545,0.0008998601,0.0008732037,0.0005079826,0.001122492,0.001917188,0.001288263,0.003835159],"category_scores_gemma":[0.007301502,0.0004502821,0.0006439841,0.0005503335,0.00055562,0.002497785,0.002115541,0.002320758,0.002124424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005045427,"about_ca_system_score_gemma":0.001019034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00448893,"about_ca_topic_score_gemma":0.01118854,"domain_scores_codex":[0.9985123,0.0007604616,0.00005824058,0.0003836711,0.0001859332,0.00009940598],"domain_scores_gemma":[0.9963434,0.001807639,0.000146851,0.001042038,0.0005120943,0.0001478788],"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":[0.0008613257,0.0004944782,0.006936207,0.0003021298,0.0002816592,0.0003919467,0.0005875633,0.1518263,0.02582265,0.005386182,0.01126239,0.7958471],"study_design_scores_gemma":[0.00002976687,0.0001899794,0.0005058175,0.00002422271,0.00004302594,0.00009457871,0.00006939345,0.9745292,0.0156776,0.006143212,0.002673717,0.00001953722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2296122,0.002173945,0.7258536,0.001103157,0.0004458361,0.0001692101,0.0008111009,0.03436064,0.005470362],"genre_scores_gemma":[0.7756906,0.0003328955,0.2140085,0.0005674875,0.0001220138,0.0001259151,0.001770994,0.001274218,0.0061073],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00448893,"threshold_uncertainty_score":0.0128299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01608260644257675,"score_gpt":0.2679565359391096,"score_spread":0.2518739294965328,"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."}}