Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset

TL;DR

This paper evaluates explainability and fairness in multilingual legal judgement prediction models using Swiss data, revealing that better predictions do not always mean better explainability, and introduces a new bias detection framework.

Contribution

It introduces a comprehensive explainability evaluation framework and a novel bias quantification method for multilingual legal judgement prediction models.

Findings

Improved prediction accuracy does not guarantee better explainability.

Models exhibit biases influenced by lower court information.

The LCI framework effectively quantifies model biases.

Abstract

The assessment of explainability in Legal Judgement Prediction (LJP) systems is of paramount importance in building trustworthy and transparent systems, particularly considering the reliance of these systems on factors that may lack legal relevance or involve sensitive attributes. This study delves into the realm of explainability and fairness in LJP models, utilizing Swiss Judgement Prediction (SJP), the only available multilingual LJP dataset. We curate a comprehensive collection of rationales that `support' and `oppose' judgement from legal experts for 108 cases in German, French, and Italian. By employing an occlusion-based explainability approach, we evaluate the explainability performance of state-of-the-art monolingual and multilingual BERT-based LJP models, as well as models developed with techniques such as data augmentation and cross-lingual transfer, which demonstrated prediction performance improvement. Notably, our findings reveal that improved prediction performance does not necessarily correspond to enhanced explainability performance, underscoring the significance of evaluating models from an explainability perspective. Additionally, we introduce a novel evaluation framework, Lower Court Insertion (LCI), which allows us to quantify the influence of lower court information on model predictions, exposing current models' biases.