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

arXiv:2409.02244 · cs.HC, cs.CL · Submitted 2024-09-03 · Read on arXiv

cs.HC, cs.CL

Submitted: 2024-09-03

Updated: 2026-09-21

Comments: To be published in CSCW 2026. Given the controlled generative synthesis of LLM sessions, this version places greater emphasis on qualitative analysis and refines the quantitative analysis accordingly, addressing methodological considerations raised during peer review regarding the interactional nature of the generated sessions and the scope of supported claims

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adam — 4× in this paper · explained in 2 episodes
• Cognitive Behavioral Therapy — 4× in this paper
• Computer Supported Cooperative Work — 4× in this paper
• AI Agents — 3× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Cognitive Therapy Rating Scale — 3× in this paper
• Core — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Intraclass Correlation Coefficient — 3× in this paper
• Regret — 3× in this paper · explained in 3 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• American Psychological Association — 2× in this paper
• Hallucination — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Sycophancy — 2× in this paper · explained in 4 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Commentary — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Hybrid System — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• A Computational Framework for Behavioral Assessment of LLM Therapists

Related papers

• EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning
• EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
• HAGI++: Head-Assisted Gaze Imputation and Generation
• Linking Behaviour and Perception to Evaluate Meaningful Human Control over Partially Automated Driving
• Review of Explainable Decision Support and Adaptive Human-Machine Interfaces for Automation Transparency in Maritime Autonomous Surface Ships
• Towards Cognitive Process-Aware Proactive Writing Support