Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency

arXiv:2309.17272v2 Announce Type: replace
Abstract: Large language models (LLMs) have exhibited remarkable ability in code generation. However, generating the correct solution in a single attempt still remains a challenge. Prior works utilize verification properties in software engineering to verify and re-rank solutions in a majority voting manner. But the assumption behind them that generated verification properties have better qualities than solutions may not always hold. In this paper, we treat them equally as different perspectives of LLMs' reasoning processes. We …

abstract arxiv challenge code code generation coding cs.ai cs.cl cs.se engineering language language models large language large language models llms perspective prior software software engineering solution solutions through type verification verify voting