PropTest: Automatic Property Testing for Improved Visual Programming

arXiv:2403.16921v1 Announce Type: new
Abstract: Visual Programming has emerged as an alternative to end-to-end black-box visual reasoning models. This type of methods leverage Large Language Models (LLMs) to decompose a problem and generate the source code for an executable computer program. This strategy has the advantage of offering an interpretable reasoning path and does not require finetuning a model with task-specific data. We propose PropTest, a general strategy that improves visual programming by further using an LLM to generate code …

abstract arxiv box code computer cs.cv generate language language models large language large language models llms path programming property reasoning strategy testing type visual