Tobias Hallmen

Tobias Hallmen

Auto-generated profile, based on publicly available information

Tobias Hallmen

Chair for Human Centered Artificial Intelligence, University of Augsburg, Augsburg, Germany

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 August 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
SESteffen T. Eberhardt
Steffen T. Eberhardt
AVAntonia Vehlen
Antonia Vehlen
JSJana Schaffrath
Jana Schaffrath
BSBrian Schwartz
Brian Schwartz
TBTobias Baur
Tobias Baur
WLWolfgang Lutz
Wolfgang Lutz
Rating scales have shaped psychological research, but are resource-intensive and can burden participants. Large Language Models (LLMs) offer a tool to assess latent constructs in text. This study introduces LLM rating scales, which use LLM responses instead of human ratings. We demonstrate this approach with an LLM rating scale measuring patient engagement in therapy transcripts. Automatically transcribed videos of 1,131 sessions from 155 patients were analyzed using DISCOVER, a software framework for local multimodal human behavior analysis. Llama 3.1 8B LLM rated 120 engagement items, averaging the top eight into a total score. Psychometric evaluation showed a normal distribution, strong reliability (ω = 0.953), and acceptable fit (CFI = 0.968, SRMR = 0.022), except RMSEA = 0.108. Validity was supported by significant correlations with engagement determinants (e.g., motivation, r = .413), processes (e.g., between-session efforts, r = .390), and outcomes (e.g., symptoms, r = − .304). Results remained robust across bootstrap resampling and cross-validation, accounting for nested data. The LLM rating scale exhibited strong psychometric properties, demonstrating the potential of the approach as an assessment tool. Importantly, this automated approach uses interpretable items, ensuring clear understanding of measured constructs, while supporting local implementation and protecting confidential data.

31 December 2025 in Medical Education Online
Verified
Journal Article
Open access
MBMoritz Bauermann
Moritz Bauermann
TRThomas Rotthoff
Thomas Rotthoff
THTobias Hallmen
Tobias Hallmen
MKMiriam Kunz
Miriam Kunz
EAElisabeth André
Elisabeth André
ASAnn-Kathrin Schindler
Ann-Kathrin Schindler
Feedback and feedforward are highly relevant in promoting students' learning. With advances in artificial intelligence (AI), new opportunities to support feedback and feedforward are emerging. However, few studies have explored how medical students perceive and accept AI-based feedback and feedforward in medical communication training. In this study, we explored medical students' perceptions of AI-based and avatar-mediated feedback and feedforward in a simulation applying a doctor-patient consultation video. The participants comprised 82 medical students (56.1% female), 66 of whom were in their second semester and 16 in their fourth semester. Before participants saw a video of a medical student in a standardized pre-recorded consultation, they were asked to put themselves in the position of the peer shown. A human-like avatar subsequently provided AI-based feedback and feedforward for the medical student in the video. The participants-still taking on the shown medical student's role-were then asked to rate the perceived trustworthiness and their potential learning acceptance of the AI-based feedback and feedforward. The participants' ratings of trustworthiness and potential learning acceptance were higher for the AI-based, avatar-mediated feedforward than the feedback. Additionally, they reported a generally positive attitude toward AI. This attitude was positively correlated with a higher potential learning acceptance of feedback. The tendency to favor feedforward over feedback in interpersonal contexts-as described in the literature-was evident for the perception of the AI-based, avatar-mediated evaluations of a simulated doctor-patient consultation video. Future research could apply these insights to enhance AI-based learning in medical education, e.g. by providing students with AI-based feedforward on their own consultation videos and assessing their perceptions of the same.

4 November 2024
Verified
Conference Paper
Open access
DDDaksitha Senel Withanage Don
Daksitha Senel Withanage Don
DSDominik Schiller
Dominik Schiller
THTobias Hallmen
Tobias Hallmen
SMSilvan Mertes
Silvan Mertes
TBTobias Baur
Tobias Baur
EAElisabeth André
Elisabeth André
Caregiver mental health disorders increase the risk of insecure infant attachment and can negatively impact multiple aspects of child development, including cognitive, emotional, and social growth. Infant-caregiver interactions contain subtle psychological and behavioral cues that reveal these adverse effects, underscoring the need for analytical methods to assess them effectively. The Face-to-Face-Still-Face (FFSF) paradigm is a key approach in psychological research for investigating these dynamics, and the Infant and Caregiver Engagement Phases revised German edition (ICEP-R) annotation scheme provides a structured framework for evaluating FFSF interactions. However, manual annotation is labor-intensive and limits scalability, thus hindering a deeper understanding of early developmental impairments. To address this, we developed a computational method that automates the annotation of caregiver-infant interactions using features extracted from audio-visual foundational models. Our approach was tested on 92 FFSF video sessions. Findings demonstrate that models based on bidirectional LSTM and linear classifiers show varying effectiveness depending on the role and feature modality. Specifically, bidirectional LSTM models generally perform better in predicting complex infant engagement phases across multimodal features, while linear models show competitive performance, particularly with unimodal feature encodings like Wav2Vec2-BERT. To support further research, we share our raw feature dataset annotated with ICEP-R labels, enabling broader refinement of computational methods in this area.

27 February 2026 in PPmP - Psychotherapie · Psychosomatik · Medizinische Psychologie
Verified
Journal Article
Open access
PDF file
EAElisabeth André
Elisabeth André
SESteffen Eberhardt
Steffen Eberhardt
THTobias Hallmen
Tobias Hallmen
AHAlexander Heimerl
Alexander Heimerl
SMSilvan Mertes
Silvan Mertes
WLWolfgang Lutz
Wolfgang Lutz
Zusammenfassung: Künstliche Intelligenz (KI) hat in den letzten Jahren große Fortschritte in der Medizin erzielt, insbesondere bei der Analyse medizinischer Bilddaten. Weniger im Fokus steht bislang ihr Potenzial als Analysetool für die Psychologie und Psychotherapie, obwohl aktuelle Entwicklungen zunehmend zeigen, dass KI-basierte Verfahren wertvolle Beiträge zur Diagnostik psychischer Störungen und zur Analyse psychotherapeutischer Gespräche leisten können. Ziel dieses Beitrags ist es, den internationalen Forschungsstand zu KI-basierten Werkzeugen und Techniken für Diagnostik und Gesprächsanalyse darzustellen, deren Potenziale und Grenzen kritisch zu diskutieren und zukünftige Anforderungen für eine verantwortungsvolle klinische Nutzung aufzuzeigen.

4 October 2026
Verified
Conference Paper
Open access
DDDaksitha Senel Withanage Don
Daksitha Senel Withanage Don
THTobias Hallmen
Tobias Hallmen
MMMitho Müller
Mitho Müller
LKLea Kaubisch
Lea Kaubisch
LSLinda Stürmlinger
Linda Stürmlinger
EAElisabeth André
Elisabeth André