修辞角色感知RAG框架用于印度最高法院判决问答
原标题：Rhetorical-Role-Aware Retrieval-Augmented Generation for Legal Question Answering over Indian Supreme Court Judgments
AI 摘要
该研究提出了一种面向印度最高法院判决书的修辞角色感知检索增强生成（RAG）框架，通过基于修辞的文本分块、融合检索和交叉编码器重排序提升检索相关性，并利用查询分类与重写及聊天历史增强多轮对话理解。评估采用DeepEval框架，在上下文召回率和答案相关性等指标上表现优异，证明了领域特定增强对构建可靠且可解释的法律AI系统的重要性。
正文节选
Computer Science > Information Retrieval Title:Rhetorical-Role-Aware Retrieval-Augmented Generation for Legal Question Answering over Indian Supreme Court Judgments View PDF HTML (experimental) Abstract:This research paper proposes a Retrieval Augmented Generation (RAG) framework that is specific to the legal field in order to assist interactive retrieval and reason about judgments from the Supreme Court of India. The solution uses an enhanced version of RAG framework which consists