View PDF (https://arxiv.org/pdf/2607.02885)HTML (experimental) (https://arxiv.org/html/2607.02885v1) Abstract:Cognitive Behavioral Therapy (CBT) provides a structured framework for understanding a user's mental state by examining the interaction between cognitive and behavioral factors. However, out-of-the-box LLMs respond fluently and empathetically, yet collapse into validation &reflection, regardless of what the user actually needs. They know theoretical CBT (scoring up to 96% accuracy on licensing exam questions) but fail to apply it effectively. We explore this gap with a knowledge-guided framework that treats CBT dialogue as controlled affective reasoning: user narratives are decomposed into Beck's Cognitive Conceptualization structure, grounded in clinical SNOMED CT concepts validated via Natural Language Inference, and a Multiple Chain-of-Thought (MCoT) strategy selection between Validation &Reflection, Socratic Questioning, or Alternative Perspectives. To measure whether such guidance actually changes behavior, we introduce the Protocol Leverage Force (F), a behavior-level metric that captures how far an intervention shifts a model away from its default response. Across three open-weight LLMs and 14 RealCBT-derived case studies, evaluated with human experts, valence-arousal trajectories, and linguistic entrainment, F shows that simply introducing protocol definitions via single chain-of-thought prompting fails to change LLM behavior, while MCoT on these definitions guides strategy selection better. Still, the effect stays within 1% (approx. 1.2-1.3%), and all models remain biased toward Validation &Reflection. These results show CBT knowledge alone does not ensure effective application, giving the affective-computing community instrumentation to measure where LLMs fall short. Comments:12 pages, 7 figures, accepted for publication in Affective Computing and Intelligent Interaction (ACII), 2026 Subjects:Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Information Retrieval (cs.IR) Cite as:arXiv:2607.02885 (https://arxiv.org/abs/2607.02885) [cs.CL] (or arXiv:2607.02885v1 (https://arxiv.org/abs/2607.02885v1) [cs.CL] for this version) https://doi.org/10.48550/arXiv.2607.02885 arXiv-issued DOI via DataCite (pending registration) Submission history From: Vaishnavi Sinha [view email (https://arxiv.org/show-email/aa168e12/2607.02885)] • *[v1]** Fri, 3 Jul 2026 02:34:08 UTC (13,078 KB)