用多样例文增强法律摘要，让内容更准更像人写。
RELexED: Retrieval-Enhanced Legal Summarization with Exemplar Diversity
- 引入例文+原文双输入，用多样性选择例文
- 在两个数据集上超越无例文和只看相似度的模型
- 适合法律文本生成与司法智能化研究者
本文针对法律摘要任务，旨在将复杂的法律文档提炼为简洁连贯的摘要。现有方法因仅依赖源文档，常出现主题偏差和风格不一致问题。我们提出RELexED，一种检索增强框架，结合源文档与例文摘要共同指导生成。该框架采用两阶段例文选择策略，利用行列式点过程平衡例文与查询的相似性与彼此间的多样性，得分基于影响函数计算。在两个法律摘要数据集上的实验表明，RELexED显著优于不使用例文或仅依赖相似性选择例文的模型。
原文摘要 · Abstract (English)
This paper addresses the task of legal summarization, which involves distilling complex legal documents into concise, coherent summaries. Current approaches often struggle with content theme deviation and inconsistent writing styles due to their reliance solely on source documents. We propose RELexED, a retrieval-augmented framework that utilizes exemplar summaries along with the source document to guide the model. RELexED employs a two-stage exemplar selection strategy, leveraging a determinantal point process to balance the trade-off between similarity of exemplars to the query and diversity among exemplars, with scores computed via influence functions. Experimental results on two legal summarization datasets demonstrate that RELexED significantly outperforms models that do not utilize exemplars and those that rely solely on similarity-based exemplar selection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。