mlsanityData to 7 Oct 2026

Detecting Conversational Mental Manipulation with Intent-Aware Prompting

arXiv 2412.08414 ↗First posted 11 Dec 2024cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 13 of its 27 references that are in the map. First posted on arXiv 11 Dec 2024.

Builds on

13 of 27 references.

References · 13

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2023Boosting Theory-of-Mind Performance in Large Language Models via Promptingcited by 64
  4. 2024Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theorycited by 60
  5. 2024CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answeringcited by 45
  6. 2023When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Taskscited by 37
  7. 2023Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Promptingcited by 31
  8. 2021Defining and Detecting Toxicity on Social Media: Context and Knowledge are Keycited by 29
  9. 2024MentalManip: A Dataset For Fine-grained Analysis of Mental Manipulation in Conversationscited by 21
  10. 2024Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answeringcited by 12
  11. 2024Enhanced Detection of Conversational Mental Manipulation Through Advanced Prompting Techniquescited by 7
  12. 2024Multi-Session Client-Centered Treatment Outcome Evaluation in Psychotherapycited by 5
1 more
  1. 2024Domain-specific Guided Summarization for Mental Health Postscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 5.

16 papers.

Sort:

By area:

  1. 2025A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directionscited by 12
  2. 2025Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacementcited by 10
  3. 2025You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversationscited by 7
  4. 2025Who's Laughing Now? An Overview of Computational Humour Generation and Explanationcited by 5
  5. 2025ChatbotManip: A Dataset to Facilitate Evaluation and Oversight of Manipulative Chatbot Behaviourcited by 4
  6. 2025Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulationcited by 3
  7. 2026Overview of the PsyDefDetect Shared Task at BioNLP 2026: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversationscited by 3
  8. 2025Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillationcited by 2
  9. 2025SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversationscited by 2
  10. 2025Detecting Malicious AI Agents Through Simulated Interactionscited by 1
  11. 2025CLAIM: An Intent-Driven Multi-Agent Framework for Analyzing Manipulation in Courtroom Dialoguescited by 1
  12. 2026Detecting Mental Manipulation in Speech via Synthetic Multi-Speaker Dialoguecited by 1
4 more
  1. 2025Explainable Detection of Implicit Influential Patterns in Conversations via Data Augmentationcited by 0
  2. 2026AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safetycited by 0
  3. 2026SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialoguecited by 0
  4. 2026Steering the Compass: Aligning Dynamic Psychological Counseling Conversations with Cognitive Behavioral Therapy Strategiescited by 0