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.

本文引入 RST-LoRA，提出了四种 RST 感知的变体，明确将 RST 融入 LoRA 模型，评估结果表明，引入修辞关系的类型和不确定性可以有效增强 LoRA 在摘要任务中的性能，最佳性能的变体优于普通的 LoRA 和全参数微调模型，并超过以往最先进的方法。