SwiLTra-Bench: The Swiss Legal Translation Benchmark


Date

2025-03

Publication Type

Working Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

In Switzerland legal translation is uniquely im portant due to the country’s four official languages and requirements for multilingual legal documentation. However, this process traditionally relies on professionals who must be both legal experts and skilled translators — creating bottlenecks and impacting effective access to justice. To address this challenge, we introduce SwiLTra-Bench, a comprehensive multilingual benchmark of over 180K aligned Swiss legal translation pairs comprising laws, headnotes, and press releases across all Swiss languages along with English, designed to evaluate LLM-based translation systems. Our systematic evaluation reveals that frontier models achieve superior translation performance across all document types, while specialized translation systems excel specifically in laws but under-perform in headnotes. Through rigorous testing and human expert validation, we demonstrate that while fine-tuning open SLMs significantly improves their translation quality, they still lag behind the best zero-shot prompted frontier models such as Claude-3.5-Sonnet. Additionally, we present SwiLTra-Judge, a specialized LLM evaluation system that aligns best with human expert assessments.

Publication status

published

Editor

Book title

Volume

05/2025

Pages / Article No.

Publisher

ETH Zurich, Center for Law & Economics

Event

Edition / version

First version

Methods

Software

Geographic location

Date collected

Date created

Subject

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Organisational unit

03795 - Bechtold, Stefan / Bechtold, Stefan check_circle

Notes

Funding