Detecting Conversational Mental Manipulation with Intent-Aware Prompting

arXiv:2412.08414v2 Announce Type: replace Abstract: Mental manipulation severely undermines mental wellness by covertly and negatively distorting decision-making. While there is an increasing interest in mental health care within the natural language processing community, progress in tackling manipulation remains limited due to the complexity of detecting subtle, covert tactics in conversations. In this paper, we propose Intent-Aware Prompting (IAP), a novel approach for detecting mental manipulations using large language models (LLMs), providing a deeper understanding of manipulative tactics by capturing the underlying intents of participants. Experimental results on the MentalManip dataset demonstrate superior effectiveness of IAP against other advanced prompting strategies. Notably, our approach substantially reduces false negatives, helping detect more instances of mental manipulation with minimal misjudgment of positive cases. The code of this paper is available.

Related

• Distinguishing Artificial from Authentic: Evaluating LLMs for Detecting LLM-Generated Content
• DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection
• Cross-Prompt Generalization in Detecting AI-Generated Fake News Using Interpretable Linguistic Features
• Context-Aware Detection and Victim-Centered Response Generation for Online Harassment in Private Messaging

Source: arXiv cs.CL | 2026-09-04