Legal Case Retrieval
Legal case retrieval aims to efficiently identify relevant prior case law for a given query, assisting legal professionals in research and decision-making. Current research heavily utilizes large language models (LLMs) and knowledge graphs, often incorporating techniques like case reformulation, structural word alignment, and multi-view contrastive learning to improve retrieval accuracy and interpretability. This field is crucial for enhancing judicial efficiency and fairness, with ongoing efforts focused on developing more robust and explainable models, as well as creating larger, higher-quality datasets for training and evaluation.
Papers
DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment
Haitao Li, Qingyao Ai, Xinyan Han, Jia Chen, Qian Dong, Yiqun Liu, Chong Chen, Qi Tian
Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval
Shengjie Ma, Chong Chen, Qi Chu, Jiaxin Mao