Harnessing the Power of Large Language Model for Effective Web API Recommendation
- 3 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (7) , 5360-5370
Abstract
Various Web API Recommendation (AR) techniques have assisted developers in efficiently identifying suitable APIs for mashup creation. With the emergence of large language models (LLMs), there has been increasing interest in leveraging LLMs for recommender systems. Although several approaches have attempted to utilize LLMs by framing recommendations as prompts, this approach is not ideally suited for AR due to fundamental differences in the training processes of LLMs and AR models. Consequently, it's crucial to conduct further research to identify effective applications of LLMs in AR. To this end, we propose a novel LLM-based generative solution for API Recommendation (LLMAR) that combines instruction learning of multitask and multistage Low-Rank Adaptation fine-tuning based on LLaMA models. Experimental results on the ProgrammableWeb dataset show that LLMAR significantly outperforms representative methods in regular and data-limited scenarios.Keywords
Funding Information
- National Natural Science Foundation of China (61962061, 62362069)
- Yunnan Fundamental Research Project (202401BF070001-024)
This publication has 29 references indexed in Scilit:
- MVGCL: Multi-View Graph Contrastive Learning for Service Recommendation2023
- Functional and Structural Fusion based Web API Recommendations in Heterogeneous Networks2023
- Web API recommendation via combining graph attention representation and deep factorization machines quality predictionConcurrency and Computation: Practice and Experience, 2022
- ServiceBERT: A Pre-trained Model for Web Service Tagging and Recommendation2021
- API recommendation for Mashup creation based on neural graph collaborative filteringConnection Science, 2021
- A novel knowledge graph embedding based API recommendation method for Mashup developmentWorld Wide Web, 2021
- Regularizing Matrix Factorization with Implicit User Preference Embeddings for Web API Recommendation2019
- Mashup-Oriented API Recommendation via Random Walk on Knowledge GraphIEEE Access, 2018
- Deep hybrid collaborative filtering for Web service recommendationExpert Systems with Applications, 2018
- Automatic Generation and Recommendation for API Mashups2017