{"ID":2847657,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.27556","arxiv_id":"2510.27556","title":"Data-Efficient Domain Adaptation for LLM-based MT using Contrastive Preference Optimization","abstract":"LLMs often require adaptation to domain-specific requirements, a process that can be expensive when relying solely on SFT. We present an empirical study on applying CPO to simulate a post-editing workflow for data-efficient domain adaptation. Our approach synthesizes preference pairs by treating the base model's own raw output as the 'rejected' translation and the human-approved TM entry as the 'chosen' one. This method provides direct feedback on the model's current knowledge, guiding it to align with domain-specific standards. Experiments in English-Brazilian Portuguese and English-Korean show that, by using just 14.7k preference pairs, the model achieves performance close to that of a model trained on 160k+ samples with SFT, demonstrating significant data efficiency. Although we showcase its effectiveness in MT, this application of CPO naturally generalizes to other generative tasks where a model's initial drafts can serve as a contrastive signal against a golden reference.","short_abstract":"LLMs often require adaptation to domain-specific requirements, a process that can be expensive when relying solely on SFT. We present an empirical study on applying CPO to simulate a post-editing workflow for data-efficient domain adaptation. Our approach synthesizes preference pairs by treating the base model's own ra...","url_abs":"https://arxiv.org/abs/2510.27556","url_pdf":"https://arxiv.org/pdf/2510.27556v1","authors":"[\"Inacio Vieira\",\"Antonio Castaldo\",\"James O'Doherty\",\"Sheila Castilho\"]","published":"2025-10-31T15:34:41Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}