EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Factually Consistent Prompting with LLMs for Cross-Lingual Dialogue Summarization

Zhongtian Bao, Wenjian Ding, Yao Zhang, Jun Wang, Zhe Sun, Andrzej Cichocki, Zhenglu Yang

Computers · 21.03.2026 · 15 (3) · 197

DOI: 10.3390/computers15030197 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 21.03.2026. Verfasst von Zhongtian Bao und 6 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Tianjin Municipal Science and Technology Bureau, Shandong Provincial Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent breakthroughs in large language models have made it feasible to effectively summarize cross-lingual dialogue information, proving essential for the global communication context. However, existing methodologies encounter difficulties in maintaining factual consistency across multiple dialogue exchanges and lack clear explanations of the summarization process. This paper presents a novel factually consistent prompting technology with large language models to address these challenges in cross-lingual dialogue summarization. First, we propose a factual replacement mechanism to enhance information analysis by incorporating noise information into summarization candidates. We adopt a self-guidance framework to enforce factual consistency, enhancing information flow tracking in cross-lingual hybrid dialogue scenarios with the assistance of GPT-based models. Furthermore, we introduce a view-aware chain-of-thought-driven architecture to improve the interpretability and transparency of the cross-lingual dialogue summarization process. Comprehensive experimental evaluations on cross-lingual summarization tasks, spanning English, French, Spanish, Russian, Chinese, and Arabic, and hybrid cross-lingual tasks substantiate that the proposed model achieves superior performance relative to state-of-the-art baselines.

Förderung

  • National Natural Science Foundation of China
  • Tianjin Municipal Science and Technology Bureau
  • Shandong Provincial Natural Science Foundation

Zitieren

APA

Bao, Z., Ding, W., Zhang, Y., Wang, J., Sun, Z., Cichocki, A., & Yang, Z. (2026). Factually Consistent Prompting with LLMs for Cross-Lingual Dialogue Summarization. Computers, 15(3), 197. https://doi.org/10.3390/computers15030197

Vancouver

Bao Z, Ding W, Zhang Y, Wang J, Sun Z, Cichocki A, et al. Factually Consistent Prompting with LLMs for Cross-Lingual Dialogue Summarization. Computers. 2026;15(3):197. doi:10.3390/computers15030197

BibTeX
@article{Bao2026,
  author = {Bao, Zhongtian and Ding, Wenjian and Zhang, Yao and Wang, Jun and Sun, Zhe and Cichocki, Andrzej and Yang, Zhenglu},
  title = {Factually Consistent Prompting with LLMs for Cross-Lingual Dialogue Summarization},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {3},
  pages = {197},
  doi = {10.3390/computers15030197}
}
Kostenlos starten →