Enhanced Detection of Conversational Mental Manipulation Through Advanced Prompting Techniques
This is an incremental improvement for detecting mental manipulation in dialogues, building on prior work.
The study investigated prompting techniques for detecting conversational mental manipulation, finding that advanced methods like Chain-of-Thought may not work well with complex models unless trained with examples.
This study presents a comprehensive, long-term project to explore the effectiveness of various prompting techniques in detecting dialogical mental manipulation. We implement Chain-of-Thought prompting with Zero-Shot and Few-Shot settings on a binary mental manipulation detection task, building upon existing work conducted with Zero-Shot and Few- Shot prompting. Our primary objective is to decipher why certain prompting techniques display superior performance, so as to craft a novel framework tailored for detection of mental manipulation. Preliminary findings suggest that advanced prompting techniques may not be suitable for more complex models, if they are not trained through example-based learning.