all AI news
Improving LLM Code Generation with Grammar Augmentation
March 5, 2024, 2:42 p.m. | Shubham Ugare, Tarun Suresh, Hangoo Kang, Sasa Misailovic, Gagandeep Singh
cs.LG updates on arXiv.org arxiv.org
Abstract: We present SynCode a novel framework for efficient and general syntactical decoding of code with large language models (LLMs). SynCode leverages the grammar of a programming language, utilizing an offline-constructed efficient lookup table called DFA mask store based on language grammar terminals. We demonstrate SynCode's soundness and completeness given the context-free grammar (CFG) of the programming language, presenting its ability to retain syntactically valid tokens while rejecting invalid ones. The framework seamlessly integrates with any …
abstract arxiv augmentation code code generation cs.fl cs.lg cs.pl cs.se decoding framework general grammar language language models large language large language models llm llms novel offline programming programming language store table type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote