Saved in:
Bibliographic Details
Main Authors: Gao, Yuansheng, Gao, Peng, Bao, Han, Li, Bin, Luo, Jixiang, Wang, Zonghui, Chen, Wenzhi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.15255
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911406417248256
author Gao, Yuansheng
Gao, Peng
Bao, Han
Li, Bin
Luo, Jixiang
Wang, Zonghui
Chen, Wenzhi
author_facet Gao, Yuansheng
Gao, Peng
Bao, Han
Li, Bin
Luo, Jixiang
Wang, Zonghui
Chen, Wenzhi
contents Mental manipulation on social media poses a covert yet serious threat to individuals' psychological well-being and the integrity of online interactions. Detecting such behavior is challenging due to the difficult-to-annotate training data, its highly covert and multi-turn nature, and the lack of real-world datasets. To address these challenges, we propose MentalMAD, a framework that enhances large language models for mental manipulation detection. Our approach consists of three key components: EvoSA, an annotation-free data augmentation method that combines evolutionary operations with speech-act-aware prompting; teacher-model-generated complementary-task supervision; and Complementary-Convergent Distillation, a phase-wise strategy for transferring manipulation-specific knowledge to student models. We then constructed the ReaMent dataset, comprising 5,000 real-world-sourced dialogues. Extensive experiments show that MentalMAD improves accuracy by 14.0%, macro-F1 by 27.3%, and weighted F1 by 15.1% over the strongest baseline. The code and the dataset are publicly available at https://github.com/Yuansheng-Gao/MentalMAD.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15255
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation
Gao, Yuansheng
Gao, Peng
Bao, Han
Li, Bin
Luo, Jixiang
Wang, Zonghui
Chen, Wenzhi
Computation and Language
Mental manipulation on social media poses a covert yet serious threat to individuals' psychological well-being and the integrity of online interactions. Detecting such behavior is challenging due to the difficult-to-annotate training data, its highly covert and multi-turn nature, and the lack of real-world datasets. To address these challenges, we propose MentalMAD, a framework that enhances large language models for mental manipulation detection. Our approach consists of three key components: EvoSA, an annotation-free data augmentation method that combines evolutionary operations with speech-act-aware prompting; teacher-model-generated complementary-task supervision; and Complementary-Convergent Distillation, a phase-wise strategy for transferring manipulation-specific knowledge to student models. We then constructed the ReaMent dataset, comprising 5,000 real-world-sourced dialogues. Extensive experiments show that MentalMAD improves accuracy by 14.0%, macro-F1 by 27.3%, and weighted F1 by 15.1% over the strongest baseline. The code and the dataset are publicly available at https://github.com/Yuansheng-Gao/MentalMAD.
title Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation
topic Computation and Language
url https://arxiv.org/abs/2505.15255