API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs

arXiv:2402.15491v1 Announce Type: new
Abstract: There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks. As such, there is tremendous interest in methods that can acquire sufficient quantities of train and test data that involve calls to tools / APIs. Two lines of research have emerged as the predominant strategies for addressing this challenge. The first has focused on synthetic data generation techniques, while the …

abstract api apis application arxiv benchmarking blend cs.ai cs.cl data interfaces language language models large language large language models llms programming tasks test tools train training type