<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>4762</id>
    <completedYear>2025</completedYear>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>381-387</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>International Educational Data Mining Society</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2025-07-20</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Comparing Human Role-Players and LLM-Simulated Clients in Online Counselling Training: An Analysis of Counselling Patterns</title>
    <abstract language="eng">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.</abstract>
    <parentTitle language="eng">Proceedings of the International Conference on Educational Data Mining</parentTitle>
    <identifier type="doi">eric.ed.gov/?id=ED675583</identifier>
    <identifier type="isbn">978-1-7336736-6-2</identifier>
    <enrichment key="ConferenceStatement">International Conference on Educational Data Mining (EDM), 18th, 2025, Palermo, Italy</enrichment>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Eric Rudolph</author>
    <author>Phillip Steigerwald</author>
    <author>Jens Albrecht</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Large Language Models</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Counselling Training</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Role Playing</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Artificial Intelligence</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Educational Technology</value>
    </subject>
    <collection role="institutes" number="">Institut für e-Beratung</collection>
    <collection role="Forschungsschwerpunkt" number="5">Digitalisierung &amp; Künstliche Intelligenz</collection>
    <collection role="institutes" number="">Zentrum für Künstliche Intelligenz (KIZ)</collection>
  </doc>
</export-example>
