{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-fine-tuning-paradox-boosting-translation","title":"The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities","arxiv_id":"2405.20089","date":"2024-05-30","proceeding":null,"authors":["David Stap","Eva Hasler","Bill Byrne","Christof Monz","Ke Tran"],"abstract":"Fine-tuning large language models (LLMs) for machine translation has shown improvements in overall translation quality. However, it is unclear what is the impact of fine-tuning on desirable LLM behaviors that are not present in neural machine translation models, such as steerability, inherent document-level translation abilities, and the ability to produce less literal translations. We perform an extensive translation evaluation on the LLaMA and Falcon family of models with model size ranging from 7 billion up to 65 billion parameters. Our results show that while fine-tuning improves the general translation quality of LLMs, several abilities degrade. In particular, we observe a decline in the ability to perform formality steering, to produce technical translations through few-shot examples, and to perform document-level translation. On the other hand, we observe that the model produces less literal translations after fine-tuning on parallel data. We show that by including monolingual data as part of the fine-tuning data we can maintain the abilities while simultaneously enhancing overall translation quality. Our findings emphasize the need for fine-tuning strategies that preserve the benefits of LLMs for machine translation.","url_abs":"https://arxiv.org/abs/2405.20089v2","url_pdf":"https://arxiv.org/pdf/2405.20089v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-fine-tuning-paradox-boosting-translation","repo_url":"https://github.com/amazon-science/idioms-incontext-mt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.20089","atlas_url":"https://app.syntology.ai/?focus=2405.20089","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}