arXiv Computation and Language September 18, 2026 By Zimu Wang, Yiwen Jiang, Xiangyu Zhao, Yaling Shen, Jiahe Liu, Stephanie Fong, Maxmartwell H Cheng, Guilherme C Oliveira, Anh Nguyen, Robert Desimone, Barnaby Nelson, Dominic Dwyer, Zongyuan Ge

Steering the Compass: Aligning Dynamic Psychological Counseling Conversations with Cognitive Behavioral Therapy Strategies

Read the original on arXiv Computation and Language →

The paper introduces StratCBT, a new dataset of 9,688 psychological counseling sessions with 256K utterances, each counselor response aligned to one of eight Cognitive Behavioral Therapy (CBT) strategies. It was created by modeling clients’ negative thoughts and generating high‑quality conversations through self‑chat, using realistic sessions for guidance. Experiments show that strategy‑aligned generation improves professional and effective counseling when evaluated with large language model‑simulated clients.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

llms

arXiv Computation and Language

Sep 1

Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs

Graph2Counsel is a framework that generates synthetic counseling dialogues by leveraging Client Psychological Graphs (CPGs) to encode the relationships among a client’s thoughts, emotions, and behaviors. The system uses a structured prompting pipeline guided by counselor strategies and explores techniques such as Chain‑of‑Thought and Multi‑Agent Feedback to produce 760 realistic sessions from 76 CPGs. Expert evaluation shows the dataset surpasses previous ones in specificity, counselor competence, authenticity, conversational flow, and safety, and fine‑tuning an open‑source model on it improves performance on several counseling benchmarks.

By Aishik Mandal, Hiba Arnaout, Clarissa W. Ong, Juliet Bockhorst, Kate Sheehan, Rachael Moldow, Tanmoy Chakraborty, Iryna Gurevych

llms agents fine-tuning safety

arXiv AI

Aug 25

DeepSAGE: Stage-Aware Reinforcement Learning for Structured CBT Counseling Dialogue

arXiv:2608.22615v1 Announce Type: new Abstract: Large Language Model (LLM)-based counseling agents can generate fluent and supportive responses, but they often lack the structured, goal-directed prog...

By Qi Zhang, Heajun An, Prakriti Dumaru, Sang Won Lee, Lifu Huang, Pamela J. Wisniewski, Jin-Hee Cho

llms agents reinforcement-learning safety

arXiv Computation and Language

4d ago

Therapy as an NLP Task: Comparing LLMs and Human Peers Behaviors in CBT Sessions

arXiv:2409.02244v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used as ad hoc therapists. While prior research has found that LLMs outperform human coun...

By Zainab Iftikhar, Sean Ransom, Amy Xiao, Nicole Nugent, Jeff Huang

llms nlp

arXiv AI

Sep 1

MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions

arXiv:2509.04183v3 Announce Type: replace-cross Abstract: The growing demand for scalable psychological counseling highlights the need for high-quality, privacy-compliant data, yet such data remains...

By Aishik Mandal, Tanmoy Chakraborty, Iryna Gurevych

llms agents fine-tuning safety

arXiv Machine Learning

Aug 6

ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance

arXiv:2608. 04524v1 Announce Type: cross Abstract: Synthetic generation of Cognitive Behavioral Therapy (CBT) sessions is challenged by two competing demands: adhering to strict therapeutic structure while modeling the resistant, unpredictable behavior of real patients.

By Javier Rodriguez-Juan, Hiba Arnaout, Jose Garcia-Rodriguez, David Tom\'as, Iryna Gurevych

agents fine-tuning safety

Hugging Face Trending Papers

Jun 3

When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling

Large Language Models (LLMs) show promise in psychological counseling, yet existing benchmarks rely heavily on highly cooperative simulated clients. We observe a critical counselor-following phenomenon: these clients often rapidly shift from resistance to compliance after only a few turns, creating an illusion of therapeutic progress and inflating scores under current evaluation protocols through superficial empathy.

llms reinforcement-learning benchmarks