Investigating Numerical Translation with Large Language Models

TL;DR

This paper evaluates the numerical translation capabilities of open-source large language models between Chinese and English, revealing significant errors especially with large units, and proposes strategies to improve accuracy.

Contribution

It systematically assesses LLMs' numerical translation accuracy and introduces mitigation strategies for large unit errors, an area previously underexplored.

Findings

Most open-source LLMs struggle with numerical translation errors.

Error rates for large units like 'million' and 'billion' can reach 20%.

Proposed strategies show potential to reduce numerical mistranslations.

Abstract

The inaccurate translation of numbers can lead to significant security issues, ranging from financial setbacks to medical inaccuracies. While large language models (LLMs) have made significant advancements in machine translation, their capacity for translating numbers has not been thoroughly explored. This study focuses on evaluating the reliability of LLM-based machine translation systems when handling numerical data. In order to systematically test the numerical translation capabilities of currently open source LLMs, we have constructed a numerical translation dataset between Chinese and English based on real business data, encompassing ten types of numerical translation. Experiments on the dataset indicate that errors in numerical translation are a common issue, with most open-source LLMs faltering when faced with our test scenarios. Especially when it comes to numerical types involving large units like ``million", ``billion", and "yi", even the latest llama3.1 8b model can have error rates as high as 20%. Finally, we introduce three potential strategies to mitigate the numerical mistranslations for large units.