SwiLTra-Bench: The Swiss Legal Translation Benchmark
This addresses bottlenecks in legal translation for Switzerland's multilingual justice system, but is incremental as it focuses on benchmarking and evaluation rather than a new translation method.
The paper tackled the challenge of legal translation in Switzerland's multilingual context by introducing SwiLTra-Bench, a benchmark of over 180K aligned translation pairs, and found that frontier models like Claude-3.5-Sonnet achieve superior performance, while fine-tuning open SLMs improves quality but still lags behind.
In Switzerland legal translation is uniquely important 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.