Newest papers

Hallucinations of Large Language Models in Cross-Language Code Translation: Phenomena and Mitigation

Yali Du, Yunji Zhang, Ming Li · 2026 · arXiv

DOI: 10.48550/arXiv.2610.27868 · open-access PDF

Korean

코드 번역은 한 프로그래밍 언어에서 다른 프로그래밍 언어로 소스 코드를 변환하면서 기능성을 보존합니다. Large Language Models (LLMs)는 코드 번역을 개선했지만, 그들의 출력에는 여전히 환각이 포함되어 있습니다 : 소스 프로그램과 충돌하는 생성된 코드, 대상 언어 사실을 위반하거나 컨텍스트적으로 불일치적인 의존성을 도입합니다. 이러한 실패는 번역에서 특히 해롭습니다.

Machine translation (Meta M2M100); the English original follows.

Abstract

Code translation converts source code from one programming language to another while preserving its functionality. Although Large Language Models (LLMs) have improved code translation, their outputs still contain hallucinations: generated code that conflicts with the source program, violates target-language facts, or introduces contextually inconsistent dependencies. These failures are especially harmful in translation because small semantic deviations can silently change program behavior. Existing hallucination studies mainly focus on natural-language generation or code generation, leaving th

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange