From Counseling Transcript to Mind Map: Leveraging LLMs for Effective Summarization in Mental Health Counseling

Julian Hao Yong, Mei Kuan Lim, Chun Yong Chong

Keywords: Large Language Models, Visual-based Summarization, Mental Health Counseling

Abstract:

The increasing number of patients with mental health illness has heightened the cognitive load on therapists, making it challenging for them to provide personalized care that each patient requires. Summarizing counseling sessions can aid mental health practitioners in recalling key details. However, most existing research on summarization focuses primarily on text-based summaries which often require significant cognitive effort to read and interpret. Visual-based summary such as mind maps is proven to help enhance cognitive understanding by giving a quick overview of topics and content. Nevertheless, due to the complex nature of counseling which involves substantial qualitative data, generating visual-based summaries using traditional AI models can be challenging. With the recent advancements in Large Language Models (LLMs), these models have demonstrated the capability to perform tasks based on instructions and generate outputs in various formats. In this study, we develop a web-based summarization tool that serves as a pipeline in performing summarization of counseling transcripts into visual-based mind map summaries using LLMs. We conducted a human evaluation to validate the effectiveness of the generated visual-based summary based on criteria of accuracy, completeness, conciseness and coherence. Our findings show that our web-based summarization tool can effectively extract key points from counseling transcripts and present them in visual-based mind maps, demonstrating its potential in enhancing insights for therapists, ultimately simplifying the process of documenting counseling sessions.

Primary Area: foundation or frontier models, including LLMs

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11148