18 papers
ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance
Javier Rodriguez-Juan, Hiba Arnaout, Jose Garcia-Rodriguez +2
Synthetic generation of Cognitive Behavioral Therapy (CBT) sessions is challenged by two competing demands: adhering to strict therapeutic structure while modeling the resistant, u…
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty +2
The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior. Features with clear activation…
Expert Preference-based Evaluation of Automated Related Work Generation
Furkan Åahinuç, Subhabrata Dutta, Iryna Gurevych
Expert domain writing, such as scientific writing, typically demands extensive domain knowledge. Although large language models (LLMs) show promising potential in this task, evalua…
UKP_Psycontrol at SemEval-2026 Task 2: Modeling Valence and Arousal Dynamics from Text
Darya Hryhoryeva, Amaia Zurinaga, Hamidreza Jamalabadi +1
This paper presents our system developed for SemEval-2026 Task 2. The task requires modeling both current affect and short-term affective change in chronologically ordered user-gen…
Responsible Evaluation of AI for Mental Health
Hiba Arnaout, Anmol Goel, H. Andrew Schwartz +13
Although artificial intelligence (AI) shows growing promise for mental health care, current approaches to evaluating AI tools in this domain remain fragmented and poorly aligned wi…
Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs
Aishik Mandal, Hiba Arnaout, Clarissa W. Ong +5
Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling. However, adapting LLMs to this high-risk safety-critical domain…