collaborators

7 papers

cs.CL2026

GEMCo: A Validated, Ethically Releasable Proxy for Inaccessible Counselling Data

Philipp Steigerwald, Eric Rudolph, Mara Stieler +3

This paper presents GEMCo, a releasable, human-written proxy for inaccessible counselling data: 86 complete German e-mail counselling conversations (728 messages), expert-authored…

cs.AI2026

LLARS: Enabling Domain Expert & Developer Collaboration for LLM Prompting, Generation and Evaluation

Philipp Steigerwald, Mara Stieler, Jennifer Burghardt +2

We demonstrate LLARS (LLM Assisted Research System), an open-source platform that bridges the gap between domain experts and developers for building LLM-based systems. It integrate…

cs.CL2026

Nürnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification

Philipp Steigerwald, Eric Rudolph, Jens Albrecht

Detecting levels of psychological defence mechanisms in supportive conversations is inherently ambiguous. In the PsyDefDetect shared task at BioNLP 2026 the eight positive defence…

cs.CL2026

Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations

Eric Rudolph, Philipp Steigerwald, Jens Albrecht

This paper studies how empirical dialogue-flow statistics can be incorporated into Next Dialogue Act Prediction (NDAP). A KL regularization term is proposed that aligns predicted a…

cs.CL2026

OnCoCo 1.0: A Public Dataset for Fine-Grained Message Classification in Online Counseling Conversations

Jens Albrecht, Robert Lehmann, Aleksandra Poltermann +3

This paper presents OnCoCo 1.0, a new public dataset for fine-grained message classification in online counseling. It is based on a new, integrative system of categories, designed…

cs.HC2026

From "Help" to Helpful: A Hierarchical Assessment of LLMs in Mental e-Health Applications

Philipp Steigerwald, Jens Albrecht

Psychosocial online counselling frequently encounters generic subject lines that impede efficient case prioritisation. This study evaluates eleven large language models generating…