all AI news
CodeHalu: Code Hallucinations in LLMs Driven by Execution-based Verification
May 2, 2024, 4:47 a.m. | Yuchen Tian, Weixiang Yan, Qian Yang, Qian Chen, Wen Wang, Ziyang Luo, Lei Ma
cs.CL updates on arXiv.org arxiv.org
Abstract: Large Language Models (LLMs) have made significant advancements in the field of code generation, offering unprecedented support for automated programming and assisting developers. However, LLMs sometimes generate code that appears plausible but fails to meet the expected requirements or executes incorrectly. This phenomenon of hallucinations in the coding field has not been explored. To advance the community's understanding and research on code hallucinations in LLMs, we propose a definition method for these hallucinations based on …
arxiv code cs.cl cs.se hallucinations llms type verification
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US