For long document summarization, discourse structure is important to discern the key content of the text and the differences in importance level between sentences. Unfortunately, the integration of rhetorical structure theory (RST) into parameter-efficient fine-tuning strategies for long document summarization remains unexplored. Therefore, this paper introduces RST-LoRA and proposes four RST-aware variants to explicitly incorporate RST into the LoRA model. Our empirical evaluation demonstrates that incorporating the type and uncertainty of rhetorical relations can complementarily enhance the performance of LoRA in summarization tasks. Furthermore, the best-performing variant we introduced outperforms the vanilla LoRA and full-parameter fine-tuning models, as confirmed by multiple automatic and human evaluations, and even surpasses previous state-of-the-art methods.

翻译：在长文档摘要任务中，篇章结构对于识别文本的核心内容以及句子间的重要性差异至关重要。然而，目前尚未有研究将修辞结构理论（RST）整合到面向长文档摘要的参数高效微调策略中。为此，本文提出了RST-LoRA，并设计了四种RST感知的变体模型，以显式地将RST信息融入LoRA模型中。我们的实验评估表明，融入修辞关系的类型和不确定性信息能够互补地提升LoRA在摘要任务中的性能。此外，我们提出的最佳性能变体在多项自动评估和人工评估中均优于原始LoRA模型及全参数微调模型，甚至超越了以往的最先进方法。