T.Y.S.S, Santosh; Baumgartner, Nina; Stürmer, Matthias; Grabmair, Matthias; Niklaus, Joël (25 May 2024). Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset In: Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING). Torino (Italia). 20-25 May 2024.
|
Text
2024.lrec-main.1434.pdf - Published Version Available under License Creative Commons: Attribution-Noncommercial (CC-BY-NC). Download (2MB) | Preview |
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.
Item Type: |
Conference or Workshop Item (Paper) |
|---|---|
Division/Institute: |
Business School > Institute for Public Sector Transformation Business School > Institute for Public Sector Transformation > Digital Sustainability Lab Business School |
Name: |
T.Y.S.S, Santosh; Baumgartner, Nina; Stürmer, Matthias  0000-0001-9038-4041; Grabmair, Matthias and Niklaus, Joël 0000-0002-2779-1653 |
Subjects: |
Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Series: |
2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings |
Language: |
English |
Submitter: |
Matthias Stürmer |
Date Deposited: |
27 Aug 2024 15:37 |
Last Modified: |
27 Aug 2024 15:37 |
Related URLs: |
|
Uncontrolled Keywords: |
Fairness Explainability Multilingual Legal Judgement Prediction |
ARBOR DOI: |
10.24451/arbor.22327 |
URI: |
https://arbor.bfh.ch/id/eprint/22327 |
Actions (login required)
 |
View Item |