The application of large language models in coaching: A knowledge-based framework for AI-Driven coaching.
Saved in:
| Title: | The application of large language models in coaching: A knowledge-based framework for AI-Driven coaching. |
|---|---|
| Authors: | Xie, Lixian (AUTHOR), Ostrowski, Erek J. (AUTHOR) |
| Source: | International Coaching Psychology Review. Atumn2025, Vol. 20 Issue 2, p83-97. 15p. |
| Subjects: | Language models, Coaching (Athletics), Humanistic psychology, Individual development, Privacy, Acceptance (Psychology) |
| Abstract: | Coaching is the practice of facilitating individuals' learning, growth, performance, and wellbeing. The rapid advancement of artificial intelligence (AI), particularly through the development of large language models (LLMs), has demonstrated remarkable potential across various fields, including coaching. This study investigates the transformative role of LLMs in coaching. It investigates individuals' receptivity to AI-driven coaching through a survey involving 49 university students. Results indicate a strong openness to AI coaching, with over 50% of participants expressing a willingness to use such tools while also raising concerns about privacy, effectiveness, and cultural understanding. This paper also proposes a knowledge-based framework for AI-driven coaching rooted in prominent psychological theories and coaching models. Through a structured three-step process, the framework enables LLMs to emulate professional coaching practices by leveraging prompt engineering and psychological insights to deliver personalised, accessible, cost-effective, and scalable coaching. This study underscores the significant potential of AI-driven coaching to promote human wellbeing and personal development at scale while laying a foundation for future research to further validate its efficacy and applications. [ABSTRACT FROM AUTHOR] |
| Copyright of International Coaching Psychology Review is the property of British Psychological Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Psychology and Behavioral Sciences Collection |
|
Full text is not displayed to guests.
Login for full access.
|
|
Be the first to leave a comment!
