基于意图感知提示的对话式心理操纵检测
Detecting Conversational Mental Manipulation with Intent-Aware Prompting
AI总结：
该研究针对对话中心理操纵检测的复杂性，提出意图感知提示（IAP）方法，在MentalManip数据集上验证其可减少假阴性、提升检测效果，相关代码已公开。
摘要：
心理操纵通过隐蔽且负面地扭曲决策，严重损害心理健康。尽管自然语言处理领域对心理健康护理的兴趣日益浓厚，但由于对话中微妙隐蔽策略的检测复杂性，解决操纵问题的进展仍然有限。本文提出了意图感知提示（Intent-Aware Prompting, IAP），这是一种使用大型语言模型（Large Language Models, LLMs）检测心理操纵的新方法，通过捕捉对话参与者的潜在意图，实现对操纵策略的更深入理解。在MentalManip数据集上的实验结果表明，与其他先进提示策略相比，IAP具有更优异的有效性；值得注意的是，该方法大幅减少了假阴性，能在最小化对正例误判的同时，检测到更多心理操纵实例。本文代码可用。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
