{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T10:20:02Z","timestamp":1772619602776,"version":"3.50.1"},"reference-count":44,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502051"],"award-info":[{"award-number":["62502051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20251101"],"award-info":[{"award-number":["GZC20251101"]}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2025A1515010267"],"award-info":[{"award-number":["2025A1515010267"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Postdoctoral Research Project Sustentation Funds of Shaanxi","award":["2024BSHSDZZ112"],"award-info":[{"award-number":["2024BSHSDZZ112"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["XJ2024008101"],"award-info":[{"award-number":["XJ2024008101"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Machine translation with large language models has recently attracted growing attention due to its flexibility and strong zero-shot and few-shot capabilities. However, most prompt-based LLM translation methods rely on linear generation or shallow self-refinement, implicitly committing to a single reasoning path. Such designs are brittle when translating long and syntactically complex sources, where reliable translation often requires structured planning and hypothesis exploration. In this paper, we propose TransGoT, a novel machine translation framework inspired by the graph-of-thoughts paradigm, which formulates translation as a structured, multi-stage reasoning process over a graph of intermediate thoughts. TransGoT explicitly decomposes translation into constraint identification, draft generation, and culture- and style-aware refinement, enabling systematic exploration and aggregation of alternative translation hypotheses. To better adapt graph-based reasoning to translation, we design two key mechanisms: (1) Uncertainty-driven thought transformation. Unlike general reasoning tasks, translation uncertainty is often localized and unevenly distributed across tokens, making holistic regeneration inefficient. We therefore design uncertainty-driven thought transformation, which leverages model-internal confidence signals to guide targeted token-level revision; (2) Dispersion-adaptive thought scoring. It emphasizes evaluation criteria with stronger inter-candidate variance to enable robust multi-criteria thought selection. We evaluate TransGoT on the WMT22 benchmarks and experimental results demonstrate that TransGoT consistently outperforms strong LLM-based translation baselines, validating the effectiveness of structured graph-based reasoning for machine translation.<\/jats:p>","DOI":"10.3390\/bdcc10030070","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T17:05:16Z","timestamp":1772211916000},"page":"70","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TransGoT: Structured Graph-of-Thoughts Reasoning for Machine Translation with Large Language Models"],"prefix":"10.3390","volume":"10","author":[{"given":"Danying","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Chang\u2019an University, Xi\u2019an 710064, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Chang\u2019an University, Xi\u2019an 710064, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Chang\u2019an University, Xi\u2019an 710064, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7191-7348","authenticated-orcid":false,"given":"Cai","family":"Xu","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University, Guangzhou 510555, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1380584.1380586","article-title":"Statistical machine translation","volume":"40","author":"Lopez","year":"2008","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1613\/jair.1.12007","article-title":"Neural machine translation: A review","volume":"69","author":"Stahlberg","year":"2020","journal-title":"J. Artif. Intell. Res."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Koehn, P., Och, F.J., and Marcu, D. (2003). Statistical phrase-based translation. Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Association for Computational Linguistics.","DOI":"10.3115\/1073445.1073462"},{"key":"ref_4","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_5","unstructured":"Bahdanau, D., Cho, K., and Bengio, Y. (2015, January 7\u20139). Neural machine translation by jointly learning to align and translate. Proceedings of the 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA."},{"key":"ref_6","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_7","unstructured":"Zhang, B., Haddow, B., and Birch, A. (2023, January 23\u201329). Prompting large language model for machine translation: A case study. Proceedings of the International Conference on Machine Learning, PMLR, Honolulu, HI, USA."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhu, D., Chen, P., Zhang, M., Haddow, B., Shen, X., and Klakow, D. (2024). Fine-tuning large language models to translate: Will a touch of noisy data in misaligned languages suffice?. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.emnlp-main.24"},{"key":"ref_9","unstructured":"Xu, H., Kim, Y.J., Sharaf, A., and Awadalla, H.H. (2024, January 7\u201311). A paradigm shift in machine translation: Boosting translation performance of large language models. Proceedings of the Twelfth International Conference on Learning Representations (ICLR), Vienna, Austria."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Dong, Y., Lyu, X., Li, J., Wei, D., Zhang, M., Tao, S., and Yang, H. (August, January 27). Two intermediate translations are better than one: Fine-tuning LLMs for document-level translation refinement. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025, Volume 1: Long Papers), Vienna, Austria.","DOI":"10.18653\/v1\/2025.acl-long.726"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1162\/tacl_a_00343","article-title":"Multilingual denoising pre-training for neural machine translation","volume":"8","author":"Liu","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Xue, L., Constant, N., Roberts, A., Kale, M., Al-Rfou, R., Siddhant, A., Barua, A., and Raffel, C. (2021, January 6\u201311). mT5: A massively multilingual pre-trained text-to-text transformer. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online.","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Alves, D., Guerreiro, N., Alves, J., Pombal, J., Rei, R., de Souza, J., Colombo, P., and Martins, A.F. (2023, January 6\u201310). Steering large language models for machine translation with finetuning and in-context learning. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore.","DOI":"10.18653\/v1\/2023.findings-emnlp.744"},{"key":"ref_14","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Vilar, D., Freitag, M., Cherry, C., Luo, J., Ratnakar, V., and Foster, G. (2023, January 9\u201314). Prompting palm for translation: Assessing strategies and performance. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.acl-long.859"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Karpinska, M., and Iyyer, M. (2023, January 6\u20137). Large language models effectively leverage document-level context for literary translation, but critical errors persist. Proceedings of the Eighth Conference on Machine Translation (WMT 2023), Singapore.","DOI":"10.18653\/v1\/2023.wmt-1.41"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1162\/tacl_a_00642","article-title":"Exploring human-like translation strategy with large language models","volume":"12","author":"He","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hu, K., Chen, Z., Yang, C.H.H., \u017belasko, P., Hrinchuk, O., Lavrukhin, V., Balam, J., and Ginsburg, B. (2025). Chain-of-thought prompting for speech translation. Proceedings of the ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP49660.2025.10890560"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Feng, Z., Zhang, Y., Li, H., Wu, B., Liao, J., Liu, W., Lang, J., Feng, Y., Wu, J., and Liu, Z. (2025). Tear: Improving llm-based machine translation with systematic self-refinement. Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.findings-naacl.218"},{"key":"ref_20","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_21","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume":"36","author":"Yao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Besta, M., Blach, N., Kubicek, A., Gerstenberger, R., Podstawski, M., Gianinazzi, L., Gajda, J., Lehmann, T., Niewiadomski, H., and Nyczyk, P. (2024, January 20\u201327). Graph of thoughts: Solving elaborate problems with large language models. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yao, B., Jiang, M., Bobinac, T., Yang, D., and Hu, J. (2024). Benchmarking machine translation with cultural awareness. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.findings-emnlp.765"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kim, D., Baek, Y., Yang, S., and Choo, J. (2023). Towards Formality-Aware Neural Machine Translation by Leveraging Context Information. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-emnlp.494"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xiao, Y., and Wang, W.Y. (2021, January 19\u201323). On hallucination and predictive uncertainty in conditional language generation. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021): Main Volume, Online.","DOI":"10.18653\/v1\/2021.eacl-main.236"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Geng, J., Cai, F., Wang, Y., Koeppl, H., Nakov, P., and Gurevych, I. (2024). A survey of confidence estimation and calibration in large language models. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.naacl-long.366"},{"key":"ref_27","unstructured":"Alves, D.M., Pombal, J., Guerreiro, N.M., Martins, P.H., Alves, J., Farajian, A., Peters, B., Rei, R., Fernandes, P., and Agrawal, S. (2024, January 7\u20139). Tower: An open multilingual large language model for translation-related tasks. Proceedings of the First Conference on Language Modeling, Philadelphia, PA, USA."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Stap, D., Hasler, E., Byrne, B., Monz, C., and Tran, K.M. (2024). The fine-tuning paradox: Boosting translation quality without sacrificing LLM abilities. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.acl-long.336"},{"key":"ref_29","unstructured":"Maslej, N., Fattorini, L., Perrault, R., Gil, Y., Parli, V., Kariuki, N., Capstick, E., Reuel, A., Brynjolfsson, E., and Etchemendy, J. (2025). Artificial Intelligence Index Report 2025. arXiv."},{"key":"ref_30","unstructured":"Awadalla, H.H. (2026, February 25). How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation. Microsoft Research, Available online: https:\/\/www.microsoft.com\/en-us\/research\/publication\/how-good-are-gpt-models-at-machine-translation-a-comprehensive-evaluation\/."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Robinson, N., Ogayo, P., Mortensen, D.R., and Neubig, G. (2023, January 6\u20137). ChatGPT MT: Competitive for high- (but not low-) resource languages. Proceedings of the Eighth Conference on Machine Translation (WMT 2023), Singapore.","DOI":"10.18653\/v1\/2023.wmt-1.40"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Agrawal, S., Zhou, C., Lewis, M., Zettlemoyer, L., and Ghazvininejad, M. (2023). In-context examples selection for machine translation. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-acl.564"},{"key":"ref_33","unstructured":"Chen, P., Guo, Z., Haddow, B., and Heafield, K. (2024). Iterative translation refinement with large language models. Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1), Association for Computational Linguistics."},{"key":"ref_34","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Madaan, A., Hermann, K., and Yazdanbakhsh, A. (2023). What makes chain-of-thought prompting effective? a counterfactual study. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-emnlp.101"},{"key":"ref_36","unstructured":"Wang, X., Wei, J., Schuurmans, D., Le, Q.V., Chi, E.H., Narang, S., Chowdhery, A., and Zhou, D. (2023, January 1\u20135). Self-consistency improves chain of thought reasoning in language models. Proceedings of the Eleventh International Conference on Learning Representations (ICLR), Kigali, Rwanda."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Raunak, V., Sharaf, A., Wang, Y., Awadalla, H., and Menezes, A. (2023). Leveraging GPT-4 for automatic translation post-editing. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-emnlp.804"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Nguyen, L., and Xu, Y. (2025). Reasoning for Translation: Comparative Analysis of Chain-of-Thought and Tree-of-Thought Prompting for LLM Translation. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.acl-srw.17"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., and Birch, A. (2016). Controlling politeness in neural machine translation via side constraints. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics.","DOI":"10.18653\/v1\/N16-1005"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Kocmi, T., and Federmann, C. (2023). GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4. Proceedings of the Eighth Conference on Machine Translation, WMT 2023, Singapore, 6\u20137 December 2023, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.wmt-1.64"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Fernandes, P., Deutsch, D., Finkelstein, M., Riley, P., Martins, A.F.T., Neubig, G., Garg, A., Clark, J.H., Freitag, M., and Firat, O. (2023, January 6\u20137). The devil is in the errors: Leveraging large language models for fine-grained machine translation evaluation. Proceedings of the Eighth Conference on Machine Translation (WMT 2023), Singapore.","DOI":"10.18653\/v1\/2023.wmt-1.100"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kocmi, T., Bawden, R., Bojar, O., Dvorkovich, A., Federmann, C., Fishel, M., Gowda, T., Graham, Y., Grundkiewicz, R., and Haddow, B. (2022, January 7\u20138). Findings of the 2022 conference on machine translation (WMT22). Proceedings of the Seventh Conference on Machine Translation (WMT), Abu Dhabi, United Arab Emirates.","DOI":"10.18653\/v1\/2022.wmt-1.1"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Rei, R., Treviso, M., Guerreiro, N.M., Zerva, C., Farinha, A.C., Maroti, C., De Souza, J.G., Glushkova, T., Alves, D., and Coheur, L. (2022). CometKiwi: IST-unbabel 2022 submission for the quality estimation shared task. Proceedings of the Seventh Conference on Machine Translation (WMT), Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.wmt-1.60"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1162\/tacl_a_00683","article-title":"xcomet: Transparent machine translation evaluation through fine-grained error detection","volume":"12","author":"Guerreiro","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/3\/70\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T05:36:41Z","timestamp":1772602601000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/3\/70"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,27]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["bdcc10030070"],"URL":"https:\/\/doi.org\/10.3390\/bdcc10030070","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,27]]}}}