EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TransGoT: Structured Graph-of-Thoughts Reasoning for Machine Translation with Large Language Models

Danying Zhang, Yixin Liu, Jie Zhao, Cai Xu

Big Data and Cognitive Computing · 27.02.2026 · 10 (3) · 70

DOI: 10.3390/bdcc10030070 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 27.02.2026. Verfasst von Danying Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Postdoctoral Fellowship Program of CPSF, Guangdong Basic and Applied Basic Research Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Natural Science Foundation of China
  • Postdoctoral Fellowship Program of CPSF
  • Guangdong Basic and Applied Basic Research Foundation
  • Postdoctoral Research Project Sustentation Funds of Shaanxi
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Zhang, D., Liu, Y., Zhao, J., & Xu, C. (2026). TransGoT: Structured Graph-of-Thoughts Reasoning for Machine Translation with Large Language Models. Big Data and Cognitive Computing, 10(3), 70. https://doi.org/10.3390/bdcc10030070

Vancouver

Zhang D, Liu Y, Zhao J, Xu C. TransGoT: Structured Graph-of-Thoughts Reasoning for Machine Translation with Large Language Models. Big Data and Cognitive Computing. 2026;10(3):70. doi:10.3390/bdcc10030070

BibTeX
@article{Zhang2026,
  author = {Zhang, Danying and Liu, Yixin and Zhao, Jie and Xu, Cai},
  title = {TransGoT: Structured Graph-of-Thoughts Reasoning for Machine Translation with Large Language Models},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {3},
  pages = {70},
  doi = {10.3390/bdcc10030070}
}
Kostenlos starten →