GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval

TL;DR

GLIER is a novel framework for legal case retrieval that uses generative inference over latent legal variables and evidence ranking to improve relevance and interpretability.

Contribution

GLIER introduces a two-stage interpretability-driven approach combining generative inference and evidence fusion for legal retrieval tasks.

Findings

GLIER outperforms baseline models like SAILER and KELLER on LeCaRD datasets.

GLIER maintains strong performance with only 10% of training data.

The framework enhances interpretability by explicitly modeling legal variables.

Abstract

The semantic gap between colloquial user queries and professional legal documents presents a fundamental challenge in Legal Case Retrieval (LCR). Existing dense retrieval methods typically treat LCR as a black-box semantic matching process, neglecting the explicit juridical logic that underpins legal relevance. To address this, we propose GLIER (Generative Legal Inference and Evidence Ranking), a framework that reformulates retrieval as an inference process over latent legal variables. GLIER decomposes the task into two interpretability-driven stages. First, a Joint Generative Inference module translates raw queries into latent legal indicators, including charges and legal elements, using a unified sequence-to-sequence strategy that jointly generates charges and elements to enforce logical consistency. Second, a Multi-View Evidence Fusion mechanism aggregates generative confidence with structural and lexical signals for precise ranking. Extensive experiments on LeCaRD and LeCaRDv2 demonstrate that GLIER outperforms strong baselines such as SAILER and KELLER. Notably, GLIER exhibits strong data efficiency, maintaining robust performance even when trained with only 10% of the data.