{"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/improving-machine-translation-with-human","title":"Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model","arxiv_id":"2401.12873","date":"2024-01-23","proceeding":null,"authors":["Zhiwei He","Xing Wang","Wenxiang Jiao","Zhuosheng Zhang","Rui Wang","Shuming Shi","Zhaopeng Tu"],"abstract":"Insufficient modeling of human preferences within the reward model is a major obstacle for leveraging human feedback to improve translation quality. Fortunately, quality estimation (QE), which predicts the quality of a given translation without reference, has achieved impressive alignment with human evaluations in the last two years. In this work, we investigate the potential of employing the QE model as the reward model to predict human preferences for feedback training. We first identify the overoptimization problem during QE-based feedback training, manifested as an increase in reward while translation quality declines. We examine the problem and argue that the vulnerability of the QE model might lead to high rewards for incorrect translations, resulting in overoptimization and error propagation. To address the problem, we adopt a simple yet effective method that uses heuristic rules to detect the incorrect translations and assigns a penalty term to the reward scores of them. Experimental results show that the proposed QE-based feedback training achieves consistent and significant improvements across various settings, further verified through human preference studies. Our subsequent analysis demonstrates the high data efficiency of the proposed QE-based feedback training: it outperforms systems using larger parallel corpora by a small amount of monolingual data. Our code is available at: https://github.com/zwhe99/FeedbackMT","url_abs":"https://arxiv.org/abs/2401.12873v3","url_pdf":"https://arxiv.org/pdf/2401.12873v3.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":"improving-machine-translation-with-human","repo_url":"https://github.com/zwhe99/feedbackmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2401.12873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12873"}},"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/zwhe99/feedbackmt","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/zwhe99/FeedbackMT","reach":{"status":"ok"}}],"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":5,"samples":[{"code_sha256_prefix":"4a62d89cb68ccb26","entry":"create_prompt","repo":"zwhe99/FeedbackMT","repo_kind":"official","path":"src/inference_sft.py","file_url":"https://github.com/zwhe99/FeedbackMT/blob/HEAD/src/inference_sft.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4a62d89cb68ccb26"}},{"code_sha256_prefix":"c12b55ef635e9947","entry":"pattern_match","repo":"zwhe99/FeedbackMT","repo_kind":"official","path":"src/LMFlow/utils/lm_evaluator.py","file_url":"https://github.com/zwhe99/FeedbackMT/blob/HEAD/src/LMFlow/utils/lm_evaluator.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c12b55ef635e9947"}},{"code_sha256_prefix":"249d0dda07bcb0de","entry":"read_input","repo":"zwhe99/FeedbackMT","repo_kind":"official","path":"src/inference_sft.py","file_url":"https://github.com/zwhe99/FeedbackMT/blob/HEAD/src/inference_sft.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"249d0dda07bcb0de"}},{"code_sha256_prefix":"f47fb9e7de49f89e","entry":"read_instruct","repo":"zwhe99/FeedbackMT","repo_kind":"official","path":"src/inference_sft.py","file_url":"https://github.com/zwhe99/FeedbackMT/blob/HEAD/src/inference_sft.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f47fb9e7de49f89e"}},{"code_sha256_prefix":"c65c0b4a64bac1ff","entry":"get_full_repo_name","repo":"zwhe99/FeedbackMT","repo_kind":"official","path":"src/LMFlow/experimental/RAFT-diffusion/train_text_to_image_lora.py","file_url":"https://github.com/zwhe99/FeedbackMT/blob/HEAD/src/LMFlow/experimental/RAFT-diffusion/train_text_to_image_lora.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c65c0b4a64bac1ff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}