Saved in:
Bibliographic Details
Main Authors: Khanna, Danush, Seth, Pratinav, Murali, Sidhaarth Sredharan, Guru, Aditya Kumar, Shukla, Siddharth, Tyagi, Tanuj, Chaurasia, Sandeep, Ghosh, Kripabandhu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.20679
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913860041048064
author Khanna, Danush
Seth, Pratinav
Murali, Sidhaarth Sredharan
Guru, Aditya Kumar
Shukla, Siddharth
Tyagi, Tanuj
Chaurasia, Sandeep
Ghosh, Kripabandhu
author_facet Khanna, Danush
Seth, Pratinav
Murali, Sidhaarth Sredharan
Guru, Aditya Kumar
Shukla, Siddharth
Tyagi, Tanuj
Chaurasia, Sandeep
Ghosh, Kripabandhu
contents Mental manipulation is a subtle yet pervasive form of abuse in interpersonal communication, making its detection critical for safeguarding potential victims. However, due to manipulation's nuanced and context-specific nature, identifying manipulative language in complex, multi-turn, and multi-person conversations remains a significant challenge for large language models (LLMs). To address this gap, we introduce the MultiManip dataset, comprising 220 multi-turn, multi-person dialogues balanced between manipulative and non-manipulative interactions, all drawn from reality shows that mimic real-world scenarios. For manipulative interactions, it includes 11 distinct manipulations depicting real-life scenarios. We conduct extensive evaluations of state-of-the-art LLMs, such as GPT-4o and Llama-3.1-8B, employing various prompting strategies. Despite their capabilities, these models often struggle to detect manipulation effectively. To overcome this limitation, we propose SELF-PERCEPT, a novel, two-stage prompting framework inspired by Self-Perception Theory, demonstrating strong performance in detecting multi-person, multi-turn mental manipulation. Our code and data are publicly available at https://github.com/danushkhanna/self-percept .
format Preprint
id arxiv_https___arxiv_org_abs_2505_20679
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations
Khanna, Danush
Seth, Pratinav
Murali, Sidhaarth Sredharan
Guru, Aditya Kumar
Shukla, Siddharth
Tyagi, Tanuj
Chaurasia, Sandeep
Ghosh, Kripabandhu
Computation and Language
Human-Computer Interaction
Machine Learning
Mental manipulation is a subtle yet pervasive form of abuse in interpersonal communication, making its detection critical for safeguarding potential victims. However, due to manipulation's nuanced and context-specific nature, identifying manipulative language in complex, multi-turn, and multi-person conversations remains a significant challenge for large language models (LLMs). To address this gap, we introduce the MultiManip dataset, comprising 220 multi-turn, multi-person dialogues balanced between manipulative and non-manipulative interactions, all drawn from reality shows that mimic real-world scenarios. For manipulative interactions, it includes 11 distinct manipulations depicting real-life scenarios. We conduct extensive evaluations of state-of-the-art LLMs, such as GPT-4o and Llama-3.1-8B, employing various prompting strategies. Despite their capabilities, these models often struggle to detect manipulation effectively. To overcome this limitation, we propose SELF-PERCEPT, a novel, two-stage prompting framework inspired by Self-Perception Theory, demonstrating strong performance in detecting multi-person, multi-turn mental manipulation. Our code and data are publicly available at https://github.com/danushkhanna/self-percept .
title SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations
topic Computation and Language
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2505.20679