Mitigating Harmful Erraticism in LLMs Through Dialectical Behavior Therapy Based De-Escalation Strategies

TL;DR

This research investigates the impact of a DBT-based framework on AI chatbot performance, aiming to ascertain its efficacy in yielding more reliable, safe, and accurate responses, while mitigating the occurrence of hallucinations, erratic behaviors, and other systemic issues.

Abstract

The escalating demand for personalized AI chatbot interactions, capable of dynamically adapting to user emotional states and real-time requests, has highlighted critical limitations in current development paradigms. Existing methodologies, which rely on baseline programming, custom personalities, and manual response adjustments, often prove difficult to maintain and are susceptible to errors such as hallucinations, erratic outputs, and software bugs. This paper hypothesizes that a framework rooted in human psychological principles, specifically therapeutic modalities, can provide a more robust and sustainable solution than purely technical interventions. Drawing an analogy to the simulated neural networks of AI mirroring the human brain, we propose the application of Dialectical Behavior Therapy (DBT) principles to regulate chatbot responses to diverse user inputs. This research investigates the impact of a DBT-based framework on AI chatbot performance, aiming to ascertain its efficacy in yielding more reliable, safe, and accurate responses, while mitigating the occurrence of hallucinations, erratic behaviors, and other systemic issues.

Figures (7)

• Figure 1: Proposed system flow of SUDS framework in a single user interaction with a foundational LLM
• Figure 2: Simulated conversation scenario with MARCo-AI
• Figure 3: Recorded and scored results of a PTSD scenario applied to Google Gemini 2.0
• Figure 4: Average Scores by Category for Three Evaluated Models
• Figure 5: Frequency Distribution of Scores in Responses By Baseline MARCo-AI