API Usage
API usage research centers on effectively leveraging large language models (LLMs) to interact with and utilize Application Programming Interfaces (APIs), primarily aiming to improve efficiency and accessibility of software functionalities. Current research focuses on developing robust benchmarks for evaluating LLMs' API-handling capabilities, exploring techniques like reinforcement learning and contrastive learning to enhance performance, and addressing challenges such as hallucinations and the need for efficient API retrieval and planning. This work has significant implications for software development, enabling more intuitive and automated software interactions, and also raises important considerations regarding security and data privacy in LLM-API ecosystems.
Papers
Contrastive Learning for API Aspect Analysis
G. M. Shahariar, Tahmid Hasan, Anindya Iqbal, Gias Uddin
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou, Mark Gerstein, Dahai Li, Zhiyuan Liu, Maosong Sun