{"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/direct-preference-optimization-for-neural","title":"Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding","arxiv_id":"2311.08380","date":"2023-11-14","proceeding":null,"authors":["Guangyu Yang","Jinghong Chen","Weizhe Lin","Bill Byrne"],"abstract":"Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs). However, MBR decoding is computationally expensive. We show how the recently developed Reinforcement Learning technique, Direct Preference Optimization (DPO), can fine-tune MLLMs to get the gains of MBR without any additional computation in inference. Our method uses only a small monolingual fine-tuning set and yields significantly improved performance on multiple NMT test sets compared to MLLMs without DPO.","url_abs":"https://arxiv.org/abs/2311.08380v2","url_pdf":"https://arxiv.org/pdf/2311.08380v2.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":"direct-preference-optimization-for-neural","repo_url":"https://github.com/bruceyg/dpo-mbr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"dpo","method_name":"DPO"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.08380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08380"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bruceyg/dpo-mbr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"56eeee4a8017cc42","entry":"dpo_nll_loss","repo":"bruceyg/dpo-mbr","repo_kind":"official","path":"trainers.py","file_url":"https://github.com/bruceyg/dpo-mbr/blob/HEAD/trainers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"56eeee4a8017cc42"}},{"code_sha256_prefix":"12f6803880f9b17e","entry":"extract_anthropic_prompt","repo":"bruceyg/dpo-mbr","repo_kind":"official","path":"preference_datasets.py","file_url":"https://github.com/bruceyg/dpo-mbr/blob/HEAD/preference_datasets.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12f6803880f9b17e"}},{"code_sha256_prefix":"26c18ad4372b45b6","entry":"get_max_diff_pairs","repo":"bruceyg/dpo-mbr","repo_kind":"official","path":"preference_datasets.py","file_url":"https://github.com/bruceyg/dpo-mbr/blob/HEAD/preference_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26c18ad4372b45b6"}},{"code_sha256_prefix":"78f963d7be1b9297","entry":"replacer","repo":"bruceyg/dpo-mbr","repo_kind":"official","path":"mbr.py","file_url":"https://github.com/bruceyg/dpo-mbr/blob/HEAD/mbr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78f963d7be1b9297"}},{"code_sha256_prefix":"d68f7fc7c779001a","entry":"mbr","repo":"bruceyg/dpo-mbr","repo_kind":"official","path":"mbr.py","file_url":"https://github.com/bruceyg/dpo-mbr/blob/HEAD/mbr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d68f7fc7c779001a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}