Response and Prompt Evaluation to Prevent Parasocial Relationships with Chatbots

Abstract: The development of parasocial relationships with AI agents has severe, and in some cases, tragic effects for human well-being. Yet preventing such dynamics is challenging: parasocial cues often emerge gradually in private conversations, and not all forms of emotional engagement are inherently harmful. We address this challenge by introducing a simple response evaluation framework, created by repurposing a state-of-the-art LLM, that evaluates ongoing conversations for parasocial cues in real time. To test the feasibility of this approach, we constructed a small synthetic dataset of thirty dialogues spanning parasocial, sycophantic, and neutral conversations. Iterative evaluation with five stage testing successfully identified all parasocial conversations while avoiding false positives under a tolerant unanimity rule, with detection typically occurring within the first few exchanges. These findings provide preliminary evidence that evaluation agents can provide a viable solution for the prevention of parasocial relations.