Saved in:
Bibliographic Details
Main Authors: Ma, Jiayuan, Na, Hongbin, Wang, Zimu, Hua, Yining, Liu, Yue, Wang, Wei, Chen, Ling
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.08414
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909424678862848
author Ma, Jiayuan
Na, Hongbin
Wang, Zimu
Hua, Yining
Liu, Yue
Wang, Wei
Chen, Ling
author_facet Ma, Jiayuan
Na, Hongbin
Wang, Zimu
Hua, Yining
Liu, Yue
Wang, Wei
Chen, Ling
contents 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 at https://github.com/Anton-Jiayuan-MA/Manip-IAP.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08414
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Detecting Conversational Mental Manipulation with Intent-Aware Prompting
Ma, Jiayuan
Na, Hongbin
Wang, Zimu
Hua, Yining
Liu, Yue
Wang, Wei
Chen, Ling
Computation and Language
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 at https://github.com/Anton-Jiayuan-MA/Manip-IAP.
title Detecting Conversational Mental Manipulation with Intent-Aware Prompting
topic Computation and Language
url https://arxiv.org/abs/2412.08414