Neuron Patching: Neuron-level Model Editing on Code Generation and LLMs

Large Language Models are successfully adopted in software engineering, especially in code generation. Updating these models with new knowledge is very expensive, and is often required to fully realize their value. In this paper, we propose a novel and effective model editing approach, \textsc{MENT}, to patch LLMs in coding tasks. Based on the mechanism of generative LLMs, \textsc{MENT} enables model editing in next-token predictions, and further supports common coding tasks. \textsc{MENT} is effective, efficient, and reliable. It can correct a …

code code generation coding cs.cl cs.lg cs.se editing engineering knowledge language language models large language large language models llms neuron novel paper software software engineering tasks value