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核心内容及句子间重要性差异具有关键作用。然而，修辞结构理论（RST）在长文档摘要的参数高效微调策略中的整合尚未得到探索。为此，本文提出RST-LoRA，并设计了四种RST感知变体，将RST显式融入LoRA模型。实验评估表明，融入修辞关系的类型与不确定性可互补性地提升LoRA在摘要任务中的性能。此外，所提出的最优变体在多项自动评估与人工评估中均优于原始LoRA与全参数微调模型，甚至超越了先前的最优方法。