Author ORCID Identifier
Document Type
Conference Proceeding
Publication Date
8-13-2024
Publication Title
International Conference on Disruptive Technologies, Tech Ethics and Artificial Intelligence
First Page
73
Last Page
84
DOI
https://doi-org.leo.lib.unomaha.edu/10.1007/978-3-031-66635-3_7
Abstract
This paper introduces an innovative approach to recommender systems through the development of an explainable architecture that leverages large language models (LLMs) and prompt engineering to provide natural language explanations. Traditional recommender systems often fall short in offering personalized, transparent explanations, particularly for users with varying levels of digital literacy. Focusing on the Advisor Recommender System, our proposed system integrates the conversational capabilities of modern AI to deliver clear, context-aware explanations for its recommendations. This research addresses key questions regarding the incorporation of LLMs into social recommender systems, the impact of natural language explanations on user perception, and the specific informational needs users prioritize in such interactions. A pilot study with 11 participants reveals insights into the system’s usability and the effectiveness of explanation clarity. Our study contributes to the broader human-AI interaction literature by outlining a novel system architecture, identifying user interaction patterns, and suggesting directions for future enhancements to improve decision-making processes in AI-driven recommendations.
Recommended Citation
Ashaduzzaman, M., Nguyen, T., Tsai, CH. (2024). Explaining Social Recommendations Using Large Language Models. In: de la Iglesia, D.H., de Paz Santana, J.F., López Rivero, A.J. (eds) New Trends in Disruptive Technologies, Tech Ethics, and Artificial Intelligence. DiTTEt 2024. Advances in Intelligent Systems and Computing, vol 1459. Springer, Cham. https://doi-org.leo.lib.unomaha.edu/10.1007/978-3-031-66635-3_7
Comments
This version of the Chapter has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi-org.leo.lib.unomaha.edu/10.1007/978-3-031-66635-3_7
Publisher holds a Bespoken License