SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations

• URL: http://arxiv.org/abs/2505.20679v1
• Date: Tue, 27 May 2025 03:51:25 GMT
• Title: SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations
• Abstract summary: Mental manipulation is a subtle yet pervasive form of abuse in interpersonal communication.<n>We introduce the MultiManip dataset, comprising 220 multi-turn, multi-person dialogues balanced between manipulative and non-manipulative interactions.<n>We propose SELF-PERCEPT, a novel, two-stage prompting framework inspired by Self-Perception Theory.
• Score: 3.9207535345233873
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 .

Related papers

• Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games [57.64247186502836]
  Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings.<n>In this paper, we study a representative multiplayer task, Murder Mystery Games, which require inferring hidden truths based on partial clues provided by roles with different intentions.<n>We propose a collaborative multi-agent framework for evaluating and synthesizing high-quality, role-driven multiplayer game scripts.
  arXiv  Detail & Related papers  (2026-04-13T17:16:23Z)
• MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games [70.37904949359938]
  We evaluate language models in multi-turn interactions using a suite of collaborative games that require effective communication about private information.<n>We find that language models are unable to use interactive collaboration to improve over the non-interactive baseline scenario.<n>We analyze the linguistic features of these dialogues, assessing the roles of sycophancy, information density, and discourse coherence.
  arXiv  Detail & Related papers  (2026-02-27T17:13:20Z)
• ClarifyMT-Bench: Benchmarking and Improving Multi-Turn Clarification for Conversational Large Language Models [32.099137908375546]
  ClarifyMT-Bench is a benchmark for multi-turn clarification in large language models (LLMs)<n>We construct 6,120 multi-turn dialogues capturing diverse ambiguity sources and interaction patterns.<n>We propose textbfClarifyAgent, an agentic approach that decomposes clarification into perception, forecasting, tracking, and planning.
  arXiv  Detail & Related papers  (2025-12-24T11:39:00Z)
• Generative Human-Object Interaction Detection via Differentiable Cognitive Steering of Multi-modal LLMs [85.69785384599827]
  Human-object interaction (HOI) detection aims to localize human-object pairs and the interactions between them.<n>Existing methods operate under a closed-world assumption, treating the task as a classification problem over a small, predefined verb set.<n>We propose GRASP-HO, a novel Generative Reasoning And Steerable Perception framework that reformulates HOI detection from the closed-set classification task to the open-vocabulary generation problem.
  arXiv  Detail & Related papers  (2025-12-19T14:41:50Z)
• Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions [21.974884890305365]
  We present a novel dataset derived from the social deduction game Werewolf.<n>This dataset provides synchronized video, text, with verifiable ground-truth labels for every statement.<n>We evaluate state-of-the-art MLLMs, revealing a significant performance gap.
  arXiv  Detail & Related papers  (2025-10-31T05:36:36Z)
• Context-aware Fairness Evaluation and Mitigation in LLMs [16.594400974742523]
  Large language models often display undesirable behaviors embedded in their internal representations.<n>Pruning-based methods provide a flexible and transparent way to reduce bias by adjusting the neurons responsible for certain behaviors.<n>We propose a dynamic, reversible, pruning-based framework that detects context-aware neuron activations and applies adaptive masking to modulate their influence during generation.
  arXiv  Detail & Related papers  (2025-10-21T06:13:17Z)
• FLEXI: Benchmarking Full-duplex Human-LLM Speech Interaction [49.83226596963294]
  Speech-computer human interaction enables real-time spoken dialogue systems.<n>Modelling and benchmarking these models remains a fundamental challenge.<n>We introduce FLEXI, the first benchmark for full-human spoken interaction.
  arXiv  Detail & Related papers  (2025-09-26T11:57:42Z)
• Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset [113.25650486482762]
  We introduce the Seamless Interaction dataset, a large-scale collection of over 4,000 hours of face-to-face interaction footage.<n>This dataset enables the development of AI technologies that understand dyadic embodied dynamics.<n>We develop a suite of models that utilize the dataset to generate dyadic motion gestures and facial expressions aligned with human speech.
  arXiv  Detail & Related papers  (2025-06-27T18:09:49Z)
• MentalMAC: Enhancing Large Language Models for Detecting Mental Manipulation via Multi-Task Anti-Curriculum Distillation [12.845142027768881]
  Mental manipulation is a subtle yet pervasive form of psychological abuse that poses serious threats to mental health.<n>MentalMAC is a multi-task anti-curriculum distillation method that enhances LLMs' ability to detect mental manipulation in multi-turn dialogue.<n>Our approach includes: (i) EvoSA, an unsupervised data expansion method based on evolutionary operations and speech act theory; (ii) teacher model-generated multi-task supervision; and (iii) progressive knowledge distillation from complex to simpler tasks.
  arXiv  Detail & Related papers  (2025-05-21T08:34:06Z)
• Can LLM Agents Maintain a Persona in Discourse? [3.286711575862228]
  Large Language Models (LLMs) are widely used as conversational agents, exploiting their capabilities in various sectors such as education, law, medicine, and more.<n>LLMs are often subjected to context-shifting behaviour, resulting in a lack of consistent and interpretable personality-aligned interactions.<n>We show that while LLMs can be guided toward personality-driven dialogue, their ability to maintain personality traits varies significantly depending on the combination of models and discourse settings.
  arXiv  Detail & Related papers  (2025-02-17T14:36:39Z)
• Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding [85.63710017456792]
  FuSe is a novel approach that enables finetuning visuomotor generalist policies on heterogeneous sensor modalities.<n>We show that FuSe enables performing challenging tasks that require reasoning jointly over modalities such as vision, touch, and sound.<n>Experiments in the real world show that FuSeis able to increase success rates by over 20% compared to all considered baselines.
  arXiv  Detail & Related papers  (2025-01-08T18:57:33Z)
• Visual Error Patterns in Multi-Modal AI: A Statistical Approach [0.0]
  Multi-modal large language models (MLLMs) excel at integrating text and visual data but face systematic challenges when interpreting ambiguous or incomplete visual stimuli.<n>This study leverages statistical modeling to analyze the factors driving these errors, using a dataset of geometric stimuli characterized by features like 3D, rotation, and missing face/side.
  arXiv  Detail & Related papers  (2024-11-27T01:20:08Z)
• Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Game [3.8284679578037246]
  We use the language logic game Who is Undercover?'' as an experimental platform to propose the Multi-Perspective Team Tactic (MPTT) framework. MPTT aims to cultivate LLMs' human-like language expression logic, multi-dimensional thinking, and self-perception in complex scenarios. Preliminary results show that MPTT, combined with WIU, leverages LLMs' cognitive capabilities to create a decision-making framework that can simulate real society.
  arXiv  Detail & Related papers  (2024-10-20T06:41:31Z)
• Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation [70.52558242336988]
  We focus on predicting engagement in dyadic interactions by scrutinizing verbal and non-verbal cues, aiming to detect signs of disinterest or confusion. In this work, we collect a dataset featuring 34 participants engaged in casual dyadic conversations, each providing self-reported engagement ratings at the end of each conversation. We introduce a novel fusion strategy using Large Language Models (LLMs) to integrate multiple behavior modalities into a multimodal transcript''
  arXiv  Detail & Related papers  (2024-09-13T18:28:12Z)
• PersLLM: A Personified Training Approach for Large Language Models [66.16513246245401]
  We propose PersLLM, a framework for better data construction and model tuning.<n>For insufficient data usage, we incorporate strategies such as Chain-of-Thought prompting and anti-induction.<n>For rigid behavior patterns, we design the tuning process and introduce automated DPO to enhance the specificity and dynamism of the models' personalities.
  arXiv  Detail & Related papers  (2024-07-17T08:13:22Z)
• MentalManip: A Dataset For Fine-grained Analysis of Mental Manipulation in Conversations [41.661208833153225]
  Mental manipulation is a significant form of abuse in interpersonal conversations. Our study introduces a new dataset, named $rm Msmall entalMsmall anip$, which consists of $4,000$ annotated movie dialogues. This dataset enables a comprehensive analysis of mental manipulation, pinpointing both the techniques utilized for manipulation and the vulnerabilities targeted in victims.
  arXiv  Detail & Related papers  (2024-05-26T14:27:48Z)
• What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models [50.97705264224828]
  We propose Counterfactual Inception, a novel method that implants counterfactual thinking into Large Multi-modal Models. We aim for the models to engage with and generate responses that span a wider contextual scene understanding. Comprehensive analyses across various LMMs, including both open-source and proprietary models, corroborate that counterfactual thinking significantly reduces hallucination.
  arXiv  Detail & Related papers  (2024-03-20T11:27:20Z)
• ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation [22.071450379253235]
  We introduce an innovative approach for robot manipulation that leverages the robust reasoning capabilities of Multimodal Large Language Models (MLLMs) By fine-tuning the injected adapters, we preserve the inherent common sense and reasoning ability of the MLLMs while equipping them with the ability for manipulation. Experiments in simulator and real-world show the promising performance of ManipLLM.
  arXiv  Detail & Related papers  (2023-12-24T06:38:11Z)
• Detecting and Grounding Multi-Modal Media Manipulation and Beyond [93.08116982163804]
  We highlight a new research problem for multi-modal fake media, namely Detecting and Grounding Multi-Modal Media Manipulation (DGM4) DGM4 aims to not only detect the authenticity of multi-modal media, but also ground the manipulated content. We propose a novel HierArchical Multi-modal Manipulation rEasoning tRansformer (HAMMER) to fully capture the fine-grained interaction between different modalities.
  arXiv  Detail & Related papers  (2023-09-25T15:05:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.