AI 中文总结
该研究针对印度最高法院判决的法律问答任务，提出含修辞分块、融合检索等模块的领域增强RAG框架，经DeepEval评估效果良好，凸显法律AI系统需领域特定增强。
AI 中文摘要
本研究论文提出了一种专门针对法律领域的检索增强生成（Retrieval Augmented Generation, RAG）框架，用于辅助交互式检索和推理印度最高法院的判决。该方案采用了增强版RAG框架，包含基于修辞的分块、基于融合的检索以及交叉编码器重排序方法，以提高检索信息的相关性。为改善对话效果，所提框架结合聊天历史、查询分类与重写，以理解用户在连续查询中的意图。此外，框架还考虑法律文件的结构特征，例如可能影响检索质量的法官单独姓名。评估使用DeepEval框架完成，在上下文召回率、答案相关性等指标上展现出强劲性能，证明该框架在处理需要大量上下文的法律问答任务时非常有效。结果强调了在开发可靠且可解释的法律AI系统时，领域特定增强的重要性。
英文摘要
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 of rhetorically based chunking, fusion-based retrieval, and cross encoder reranking methods to increase the relevancy of the information retrieved. In order to improve conversations, the proposed framework uses chat history along with query classification and rewriting in order to understand user intention from successive queries. Additionally, there are features that take into account structural aspects of legal documents, such as isolated names of judges that could have an impact on retrieval quality. The evaluation was done using the DeepEval framework and demonstrated strong performance on metrics including contextual recall and answer relevancy, which proves that the framework is very effective in dealing with legal question-answering tasks that require a lot of context. The results emphasize the importance of domain specific enhancements in developing legal AI systems that are both reliable and explainable.
