• search hit 2 of 99
Back to Result List

Comparing Human Role-Players and LLM-Simulated Clients in Online Counselling Training: An Analysis of Counselling Patterns

  • This study investigates the capabilities of Large Language Models to simulate counselling clients in educational roleplays in comparison to human role-players. Initially, we recorded role-playing sessions, where novice counsellors interacted with human peers acting as clients, followed by role-plays between humans and clients simulated by Mistrals Mixtral 8x7b using 4-bit quantization. These interactions were analysed with a counselling communication pattern system at sentence level. We investigated two key questions: (1) to what extent LLM-generated responses replicate authentic conversational dynamics and (2) whether counsellors’ communication behaviour differs when interacting with human versus LLM-simulated clients. The findings highlight both similarities and differences in the application of counselling patterns across scenarios, showing the potential of LLM-based role-playing exercises to enhance counselling competencies and to identify areas for further refinement in virtual client simulations.

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Eric RudolphORCiD, Phillip Steigerwald, Jens Albrecht
DOI:https://doi.org/eric.ed.gov/?id=ED675583
ISBN:978-1-7336736-6-2
Parent Title (English):Proceedings of the International Conference on Educational Data Mining
Publisher:International Educational Data Mining Society
Document Type:conference proceeding (article)
Language:English
Date of first Publication:2025/07/20
Reviewed:Begutachtet/Reviewed
Release Date:2026/04/15
Tag:Artificial Intelligence; Counselling Training; Educational Technology; Large Language Models; Role Playing
Pagenumber:381-387
Konferenzangabe:International Conference on Educational Data Mining (EDM), 18th, 2025, Palermo, Italy
institutes:Institut für e-Beratung
Zentrum für Künstliche Intelligenz (KIZ)
Research Themes:Digitalisierung & Künstliche Intelligenz
Licence (German):Creative Commons - CC BY - Namensnennung 4.0 International
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.