Semantically Aligned Question and Code Generation for Automated Insight Generation

arXiv:2405.01556v1 Announce Type: cross
Abstract: Automated insight generation is a common tactic for helping knowledge workers, such as data scientists, to quickly understand the potential value of new and unfamiliar data. Unfortunately, automated insights produced by large-language models can generate code that does not correctly correspond (or align) to the insight. In this paper, we leverage the semantic knowledge of large language models to generate targeted and insightful questions about data and the corresponding code to answer those questions. Then …

abstract arxiv automated code code generation cs.ai cs.cl cs.se data data scientists generate insight insights knowledge knowledge workers language language models question scientists type value workers