Factually Consistent Prompting with LLMs for Cross-Lingual Dialogue Summarization

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.