Genetic Auto-prompt Learning for Pre-trained Code Intelligence Language Models

arXiv:2403.13588v1 Announce Type: cross
Abstract: As Pre-trained Language Models (PLMs), a popular approach for code intelligence, continue to grow in size, the computational cost of their usage has become prohibitively expensive. Prompt learning, a recent development in the field of natural language processing, emerges as a potential solution to address this challenge. In this paper, we investigate the effectiveness of prompt learning in code intelligence tasks. We unveil its reliance on manually designed prompts, which often require significant human effort …

abstract arxiv auto become code code intelligence computational cost cs.cl cs.se development intelligence language language models language processing natural natural language natural language processing popular processing prompt prompt learning solution type usage