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

French

La traduction de code convertit le code source d'un langage de programmation à un autre tout en préservant sa fonctionnalité. Bien que les grands modèles linguistiques (LLM) aient amélioré la traduction de code, leurs sorties contiennent toujours des hallucinations: code généré qui entre en conflit avec le programme source, viole les faits de la langue cible ou introduit des dépendances contextuellement incohérentes. Ces échecs sont particulièrement nocifs dans la traduction car de petites déviations sémantiques peuvent modifier silencieusement le comportement du programme.

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27868, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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