Reversible Pseudonymisation of Documents Sent to External LLMs: an Open Bilingual Benchmark and an Engine

Summary

The author benchmarks five existing open pseudonymisation tools and a regex baseline on Russian and UK English, then builds an open engine from the two strongest. On held-out synthetic documents from the generator the engine was developed on, it leaves a whole value visible in 0.3% and 0.2% of documents, while the best existing tools do so in 61% (Russian) and 58% (UK). In Russian, name placeholders restore at only 94.6%, below the 99% threshold.