Preprint catalogs 13,919 mistakes AI models make when translating code between languages

Researchers had seven AI models translate code across six language pairs on three benchmarks and hand-labeled 13,919 cases where the output strayed from the original. They sort the errors into three types, including semantic conflicts and lost project context, and propose a fix that retrieves similar past translations.

Photo: Kevin Dooley / Wikimedia Commons, CC BY 2.0 (cropped)

Sources

• Research Yali Du, Yunji Zhang, Ming Li (arXiv, 査読前) (2026-10-20)
  Hallucinations of Large Language Models in Cross-Language Code Translation: Phenomena and Mitigation

Editorial policy ・ Terms of use