LAWRE evaluates whether legal case retrieval systems possess the reasoning skills needed in practice, beyond high recall on existing benchmarks. It provides diagnostic tests for capabilities such as distinguishing easily confused cases and identifying legal elements.

Publication

Accepted to the 2026 International Joint Conference on Neural Networks (IJCNN) and published in its proceedings, pages 1–6. The conference took place on June 22–26, 2026, in Maastricht, Netherlands.

DOI: 10.1109/IJCNN69854.2026.11728674. The paper was added to IEEE Xplore on October 19, 2026.

Overview

Strong retrieval scores do not necessarily demonstrate the legal reasoning required for practical use. LAWRE introduces a benchmark that probes these capabilities and provides detailed diagnostic feedback on legal case retrieval systems.

Evaluation

The paper evaluates eight representative retrieval models, identifying weaknesses that can guide the development of more practically effective legal case retrieval systems.

Resources