{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:22:28Z","timestamp":1773001348389,"version":"3.50.1"},"reference-count":37,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"vor","delay-in-days":287,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["242102211060"],"award-info":[{"award-number":["242102211060"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>While Large Language Models (LLMs) demonstrate strong translation capabilities, optimizing their output towards human\u2010level refinement necessitates reasoning\u2010guided approaches that move beyond simple generation. This paper introduces Multidimensional Feedback and Postedit Thought (MFPE), a novel framework specifically designed for reasoning\u2010guided LLM translation optimization. MFPE operationalizes this guidance by leveraging multidimensional postediting feedback, which acts as explicit reasoning signals to the LLM. This feedback mechanism simulates the human postediting process, where errors are systematically identified and corrected. Generated by a dedicated optimization model trained on a synthetic dataset (using GLM\u20104 and inspired by multidimensional quality metrics (MQM), this feedback provides fine\u2010grained error details including spans, categories, and quantities from initial LLM translations. We conduct experiments across four language pairs: Chinese\u2010English, German\u2010English, English\u2010Chinese, and English\u2010German. The results show that fine\u2010tuning with structured, reasoning\u2010like feedback significantly enhances translation quality and outperforms standard bilingual fine\u2010tuning approaches. Our findings highlight the effectiveness of simulating postediting reasoning through structured feedback, offering a promising direction for harnessing and improving the inferential capabilities of LLMs for complex tasks like high\u2010quality machine translation.<\/jats:p>","DOI":"10.1155\/int\/9971702","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:33:03Z","timestamp":1760596383000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reasoning\u2010Guided LLM Translation Optimization: A Framework Using Multidimensional Postediting Feedback"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0031-9244","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7916-5008","authenticated-orcid":false,"given":"Xiaogang","family":"Zang","sequence":"additional","affiliation":[]},{"given":"Chenyang","family":"Ji","sequence":"additional","affiliation":[]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"e_1_2_13_1_2","doi-asserted-by":"crossref","unstructured":"ZhuS. PanL. LiB. andXiongD. Landermt: Dectecting and Routing Language-Aware Neurons for Selectively Finetuning Llms to Machine Translation Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2024 12135\u201312148 https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.656.","DOI":"10.18653\/v1\/2024.acl-long.656"},{"key":"e_1_2_13_2_2","article-title":"Sparks of Artificial General Intelligence: Early Experiments With gpt-4","author":"Bubeck S.","year":"2023","journal-title":"arXiv preprint arXiv:2303.12712"},{"key":"e_1_2_13_3_2","doi-asserted-by":"crossref","unstructured":"ZhuS. CuiM. andXiongD. Towards Robust in-Context Learning for Machine Translation With Large Language Models Proceedings of the 2024 Joint International Conference on Computational Linguistics Language Resources and Evaluation (LREC-COLING 2024) 2024 16619\u201316629.","DOI":"10.63317\/2xcecragguex"},{"key":"e_1_2_13_4_2","unstructured":"MoghaddamS. R.andHoneyC. J. Boosting Theory-of-Mind Performance in Large Language Models via Prompting arXiv preprint arXiv:2304.11490 2023."},{"key":"e_1_2_13_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.646"},{"key":"e_1_2_13_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103825"},{"key":"e_1_2_13_7_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00642"},{"key":"e_1_2_13_8_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00437"},{"key":"e_1_2_13_9_2","doi-asserted-by":"publisher","DOI":"10.5565\/rev\/tradumatica.77"},{"key":"e_1_2_13_10_2","doi-asserted-by":"crossref","unstructured":"XuW. DeutschD. FinkelsteinM.et al. Llmrefine: Pinpointing and Refining Large Language Models via fine-grained Actionable Feedback Findings of the Association for Computational Linguistics: NAACL 2024 2024 1429\u20131445 https:\/\/doi.org\/10.18653\/v1\/2024.findings-naacl.92.","DOI":"10.18653\/v1\/2024.findings-naacl.92"},{"key":"e_1_2_13_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2025.104078"},{"key":"e_1_2_13_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-020-09249-7"},{"key":"e_1_2_13_13_2","article-title":"Automatic Post-editing for Machine Translation","author":"Chatterjee R.","year":"2019","journal-title":"arXiv preprint arXiv:1910.08592"},{"key":"e_1_2_13_14_2","unstructured":"G\u00f3isA. ChoK. andMartinsA. F. Learning Non-monotonic Automatic Post-editing of Translations from Human Orderings Proceedings of the 22nd Annual Conference of the European Association for Machine Translation 2020 205\u2013214."},{"key":"e_1_2_13_15_2","doi-asserted-by":"crossref","unstructured":"CorreiaG. M.andMartinsA. F. A Simple and Effective Approach to Automatic Post-editing With Transfer Learning 57th Annual Meeting of the Association for Computational Linguistics ACL 2019. Association for Computational Linguistics (ACL) 2020 3050\u20133056 https:\/\/doi.org\/10.18653\/v1\/p19-1292.","DOI":"10.18653\/v1\/P19-1292"},{"key":"e_1_2_13_16_2","doi-asserted-by":"crossref","unstructured":"VoitaE. SennrichR. andTitovI. Context-Aware Monolingual Repair for Neural Machine Translation EMNLP-IJCNLP 2019-2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing Proceedings of the Conference 2020 877\u2013886 https:\/\/doi.org\/10.18653\/v1\/d19-1081.","DOI":"10.18653\/v1\/D19-1081"},{"key":"e_1_2_13_17_2","doi-asserted-by":"crossref","unstructured":"ChollampattS. SusantoR. H. TanL. andSzymanskaE. Can Automatic Post-editing Improve Nmt? Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020 2736\u20132746 https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.217.","DOI":"10.18653\/v1\/2020.emnlp-main.217"},{"key":"e_1_2_13_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-020-09252-y"},{"key":"e_1_2_13_19_2","unstructured":"VidalB. LlorensA. andAlonsoJ. Automatic Post-editing of Mt Output Using Large Language Models Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track) 2022 84\u2013106."},{"key":"e_1_2_13_20_2","first-page":"181","article-title":"Iterative Translation Refinement With Large Language Models","volume":"1","author":"Chen P.","year":"2024","journal-title":"Proceedings of the 25th Annual Conference of the European Association for Machine Translation"},{"key":"e_1_2_13_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.804"},{"key":"e_1_2_13_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.265"},{"key":"e_1_2_13_23_2","article-title":"Chatglm: A Family of Large Language Models from glm-130b to glm-4 all Tools","author":"Zeng A.","year":"2024","journal-title":"CoRR"},{"key":"e_1_2_13_24_2","doi-asserted-by":"crossref","unstructured":"SellamT. DasD. andParikhA. Bleurt: Learning Robust Metrics for Text Generation Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020 7881\u20137892.","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"e_1_2_13_25_2","doi-asserted-by":"crossref","unstructured":"FuJ. NgS. K. JiangZ. andLiuP. Gptscore: Evaluate as You Desire 1 Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 2024 Long Papers 6556\u20136576.","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"e_1_2_13_26_2","doi-asserted-by":"crossref","unstructured":"FernandesP. DeutschD. FinkelsteinM.et al. The Devil is in the Errors: Leveraging Large Language Models for fine-grained Machine Translation Evaluation Proceedings of the Eighth Conference on Machine Translation 2023 1066\u20131083 https:\/\/doi.org\/10.18653\/v1\/2023.wmt-1.100.","DOI":"10.18653\/v1\/2023.wmt-1.100"},{"key":"e_1_2_13_27_2","doi-asserted-by":"crossref","unstructured":"KocmiT.andFedermannC. Gemba-Mqm: Detecting Translation Quality Error Spans With gpt-4 Proceedings of the Eighth Conference on Machine Translation 2023 768\u2013775 https:\/\/doi.org\/10.18653\/v1\/2023.wmt-1.64.","DOI":"10.18653\/v1\/2023.wmt-1.64"},{"key":"e_1_2_13_28_2","unstructured":"KocmiT.andFedermannC. Large Language Models Are state-of-the-art Evaluators of Translation Quality Proceedings of the 24th Annual Conference of the European Association for Machine Translation 2023 193\u2013203."},{"key":"e_1_2_13_29_2","doi-asserted-by":"crossref","unstructured":"LiuY. IterD. XuY. WangS. XuR. andZhuC. G-eval: Nlg Evaluation Using gpt-4 With Better Human Alignment Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing 2023 2511\u20132522.","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"e_1_2_13_30_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00683"},{"key":"e_1_2_13_31_2","doi-asserted-by":"crossref","unstructured":"ReiR. De SouzaJ. G. AlvesD.et al. Comet-22: Unbabel-Ist 2022 Submission for the Metrics Shared Task Proceedings of the Seventh Conference on Machine Translation (WMT) 2022 578\u2013585.","DOI":"10.18653\/v1\/2022.wmt-1.52"},{"key":"e_1_2_13_32_2","doi-asserted-by":"crossref","unstructured":"XuW. WangD. PanL.et al. Instructscore: Towards Explainable Text Generation Evaluation With Automatic Feedback Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing 2023 5967\u20135994.","DOI":"10.18653\/v1\/2023.emnlp-main.365"},{"key":"e_1_2_13_33_2","article-title":"Lora: Low-Rank Adaptation of Large Language Models","volume":"1","author":"Hu E. J.","year":"2022","journal-title":"ICLR"},{"key":"e_1_2_13_34_2","unstructured":"KocmiT. BawdenR. BojarO.et al. Findings of the 2022 Conference on Machine Translation (Wmt22) Proceedings of the Seventh Conference on Machine Translation (WMT) 2022 1\u201345."},{"key":"e_1_2_13_35_2","doi-asserted-by":"crossref","unstructured":"PapineniK. RoukosS. WardT. andZhuW.-J. Bleu: A Method for Automatic Evaluation of Machine Translation Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics 2002 311\u2013318 https:\/\/doi.org\/10.3115\/1073083.1073135.","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_2_13_36_2","doi-asserted-by":"crossref","unstructured":"PostM. A Call for Clarity in Reporting Bleu Scores Proceedings of the Third Conference on Machine Translation: Research Papers 2018 186\u2013191.","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_2_13_37_2","doi-asserted-by":"crossref","unstructured":"ReiR. TrevisoM. GuerreiroN. M.et al. Cometkiwi: Ist-Unbabel 2022 Submission for the Quality Estimation Shared Task 7th Conference on Machine Translation WMT 2022 2022 Association for Computational Linguistics 634\u2013645.","DOI":"10.18653\/v1\/2022.wmt-1.60"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/9971702","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/9971702","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/9971702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:58:33Z","timestamp":1772992713000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/9971702"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/9971702"],"URL":"https:\/\/doi.org\/10.1155\/int\/9971702","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-04-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"9971702"}}