LLMs often hallucinate incorrect names, especially in private codebases. We introduce Monitor-Guided Decoding (MGD)-guide LMs to generate compilable code with correct symbol names more reliably!🚀 (Work w/
@adityakanade0Navin Goyal
@LahiriShuvendu@SriramRajamani@MSFTResearch)
Guiding Language Models of Code with Global Context using Monitors paper page: huggingface.co/papers/2306.10… Language models of code (LMs) work well when the surrounding code in the vicinity of generation provides sufficient context. This is not true when it becomes necessary to use
