RESTful-Llama: Connecting User Queries to RESTful APIs

Han Xu, Ruining Zhao, Jindong Wang, Haipeng Chen


Abstract
Recent advancements in Large Language Models (LLMs) have showcased exceptional performance in zero-shot learning and reasoning tasks. However, integrating these models with external tools - a crucial need for real-world applications - remains a significant challenge. We propose RESTful-Llama, a novel framework designed to enable Llama 3.1 to transform natural language instructions into effective RESTful API calls. To enhance the fine-tuning process, we introduce DOC_Mine, a method to generate fine-tuning datasets from public API documentation. RESTful-Llama distinguishes itself by enabling open-source LLMs to efficiently interact with and adapt to any REST API system. Experiments demonstrate a 31.9% improvement in robustness and a 2.33x increase in efficiency compared to existing methods.
Anthology ID:
2024.emnlp-industry.105
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
November
Year:
2024
Address:
Miami, Florida, US
Editors:
Franck Dernoncourt, Daniel Preoţiuc-Pietro, Anastasia Shimorina
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1433–1443
Language:
URL:
https://aclanthology.org/2024.emnlp-industry.105
DOI:
Bibkey:
Cite (ACL):
Han Xu, Ruining Zhao, Jindong Wang, and Haipeng Chen. 2024. RESTful-Llama: Connecting User Queries to RESTful APIs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1433–1443, Miami, Florida, US. Association for Computational Linguistics.
Cite (Informal):
RESTful-Llama: Connecting User Queries to RESTful APIs (Xu et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-industry.105.pdf