Cassette improves legal case search with faster and accurate retrieval
Cassette: Case-to-Case Structural Distillation for Efficient Legal Case Retrieval
Information Retrieval
Summary
Finding relevant legal cases quickly can be very slow when the database is large. The authors built on previous methods that linked cases to each other but were too slow for big collections. They designed a new system called Cassette that learns from a complex model and transfers this knowledge to a faster, simpler one. This makes searching through thousands of cases much faster while still being accurate. They tested their method on several datasets and confirmed it works well.
What this means in practice
- •For legal tech developers: Create fast and accurate legal case search tools that handle large databases efficiently without sacrificing retrieval quality.
- •For document management teams: Integrate an efficient case retrieval system to help organize and access large legal document collections quickly.
Authors
Yanran Tang, Ruihong Qiu, Hongzhi Yin, Xue Li, Zi Huang
Abstract
Legal case retrieval (LCR) is an essential tool for not only assisting legal practitioners to efficiently retrieve precedents but also enabling ordinary individuals to find valuable legal case information without relying on expensive professional legal services. Our previous work CaseLink demonstrated the effectiveness of using case to case graph structures to improve retrieval accuracy. However, its high computational cost during inference on large-scale legal databases limits its practical use in real-world settings. The main inefficiency comes from constructing test time graphs and computing pairwise term frequency similarities of cases. This process has O(n^2) complexity for n legal cases, making the runtime prohibitive as the number of candidates grows. For example, the retrieval time for one query on a database (COLIEE2022) with 1,563 candidate cases is more than 500 milliseconds, while the runtime would increase drastically to more than 3,500 seconds for a database (LeCaRDv2) with 55,192 candidate cases. To further enhance the retrieval performance while achieving a significant speed-up, in this extension paper, Cassette framework is proposed with a distillation strategy involving ranking objective and eigen-matching objective for an effective transfer of knowledge from a powerful and well-trained heavy teacher retriever to a lightweight and efficient hybrid student dual encoder. Specifically, the student query encoder is implemented as a multilayer perceptron model designed for fast online processing, whereas the student candidate encoder adopts a GNN architecture, suitable for an offline manner within the case database. Extensive experiments are conducted on three benchmark datasets, and the results verify the effectiveness of the ranking distillation while achieving high efficiency. The code has been released on https://github.com/yanran-tang/Cassette/.