Investigating Numerical Translation with Large Language Models
This addresses a critical problem for users in fields like finance and medicine where numerical mistranslations can cause security issues, though it is incremental as it focuses on a specific bottleneck in existing LLM translation systems.
The study evaluated the reliability of large language models (LLMs) in translating numbers between Chinese and English, finding that errors are common, with error rates as high as 20% for large units like 'million' and 'billion' in models such as llama3.1 8b.
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.