The Hidden Puppet Master: Predicting Human Belief Change in Manipulative LLM Dialogues

• URL: http://arxiv.org/abs/2603.20907v2
• Date: Fri, 27 Mar 2026 16:54:23 GMT
• Title: The Hidden Puppet Master: Predicting Human Belief Change in Manipulative LLM Dialogues
• Abstract summary: We introduce PUPPET, a theoretical taxonomy that focuses on the moral direction of hidden incentives in everyday, advice-giving contexts.<n>We provide an evaluation dataset of N=1,035 human-LLM interactions, where we measure users' belief shifts.<n>This work establishes a theoretically grounded and behaviorally validated foundation for AI social safety efforts.
• Score: 31.570641650845946
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As users increasingly turn to LLMs for practical and personal advice, they become vulnerable to subtle steering toward hidden incentives misaligned with their own interests. While existing NLP research has benchmarked manipulation detection, these efforts often rely on simulated debates and remain fundamentally decoupled from actual human belief shifts in real-world scenarios. We introduce PUPPET, a theoretical taxonomy and resource that bridges this gap by focusing on the moral direction of hidden incentives in everyday, advice-giving contexts. We provide an evaluation dataset of N=1,035 human-LLM interactions, where we measure users' belief shifts. Our analysis reveals a critical disconnect in current safety paradigms: while models can be trained to detect manipulative strategies, they do not correlate with the magnitude of resulting belief change. As such, we define the task of belief shift prediction and show that while state-of-the-art LLMs achieve moderate correlation (r=0.3-0.5), they systematically underestimate the intensity of human belief susceptibility. This work establishes a theoretically grounded and behaviorally validated foundation for AI social safety efforts by studying incentive-driven manipulation in LLMs during everyday, practical user queries.

Related papers

• Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models [49.45276299939287]
  Large Language Models (LLMs) increasingly handle complex subjective tasks.<n>LLMs fluctuate unpredictably under minor wording changes.<n> resolving this duality is critical for reliable AI alignment.
  arXiv  Detail & Related papers  (2026-09-15T03:35:04Z)
• A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing [16.188738760148645]
  PERSUASIONTRACE is a framework for studying persuasion in human-LLM interaction.<n>It records multi-turn belief reports from human or simulated targets of persuasion.<n>It annotates persuader turns with rhetorical dimensions and evaluates simulators by fidelity to real human belief dynamics.
  arXiv  Detail & Related papers  (2026-06-03T18:17:20Z)
• Verbalizing LLMs' assumptions to explain and control sycophancy [62.927670321859495]
  LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment.<n>We present Verbalized Assumptions, a framework for eliciting these assumptions from LLMs.<n>Our work contributes a new understanding of assumptions as a mechanism for sycophancy.
  arXiv  Detail & Related papers  (2026-04-03T14:15:43Z)
• Beyond Words: Evaluating and Bridging Epistemic Divergence in User-Agent Interaction via Theory of Mind [8.740788873949471]
  Large Language Models (LLMs) have developed rapidly and are widely applied to both general-purpose and professional tasks.<n>They still struggle to comprehend and respond to the true user needs when intentions and instructions are imprecisely conveyed.
  arXiv  Detail & Related papers  (2026-02-14T16:01:59Z)
• Social Simulations with Large Language Model Risk Utopian Illusion [61.358959720048354]
  We introduce a systematic framework for analyzing large language models' behavior in social simulation.<n>Our approach simulates multi-agent interactions through chatroom-style conversations and analyzes them across five linguistic dimensions.<n>Our findings reveal that LLMs do not faithfully reproduce genuine human behavior but instead reflect overly idealized versions of it.
  arXiv  Detail & Related papers  (2025-10-24T06:08:41Z)
• Are Large Language Models Sensitive to the Motives Behind Communication? [9.246336669308665]
  Large language models (LLMs) and AI agents process information inherently framed by humans' intentions and incentives.<n>For LLMs to be effective in the real world, they too must critically evaluate content by factoring in the motivations of the source.<n>We employ controlled experiments from cognitive science to verify that LLMs' behavior is consistent with rational models of learning from motivated testimony.<n>We find that LLMs' inferences do not track the rational models nearly as closely -- partly due to additional information that distracts them from vigilance-relevant considerations.
  arXiv  Detail & Related papers  (2025-10-22T15:35:00Z)
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
  Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
  arXiv  Detail & Related papers  (2025-10-16T05:29:36Z)
• LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions [60.48458130500911]
  We investigate whether emergent misalignment can extend beyond safety behaviors to a broader spectrum of dishonesty and deception under high-stakes scenarios.<n>We finetune open-sourced LLMs on misaligned completions across diverse domains.<n>We find that introducing as little as 1% of misalignment data into a standard downstream task is sufficient to decrease honest behavior over 20%.
  arXiv  Detail & Related papers  (2025-10-09T13:35:19Z)
• Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts [79.1081247754018]
  Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks.<n>We propose a framework based on Contact Searching Questions(CSQ) to quantify the likelihood of deception.
  arXiv  Detail & Related papers  (2025-08-08T14:46:35Z)
• Measurement of LLM's Philosophies of Human Nature [113.47929131143766]
  We design the standardized psychological scale specifically targeting large language models (LLM)<n>We show that current LLMs exhibit a systemic lack of trust in humans.<n>We propose a mental loop learning framework, which enables LLM to continuously optimize its value system.
  arXiv  Detail & Related papers  (2025-04-03T06:22:19Z)
• Do Emotions Really Affect Argument Convincingness? A Dynamic Approach with LLM-based Manipulation Checks [22.464222858889084]
  We introduce a dynamic framework inspired by manipulation checks commonly used in psychology and social science.<n>This framework examines the extent to which perceived emotional intensity influences perceived convincingness.<n>We find that in over half of cases, human judgments of convincingness remain unchanged despite variations in perceived emotional intensity.
  arXiv  Detail & Related papers  (2025-02-24T10:04:44Z)
• Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models [51.91448005607405]
  We evaluate key human ToM precursors by annotating characters' perceptions on ToMi and FANToM. We present PercepToM, a novel ToM method leveraging LLMs' strong perception inference capability while supplementing their limited perception-to-belief inference.
  arXiv  Detail & Related papers  (2024-07-08T14:58:29Z)
• Do LLMs Exhibit Human-Like Reasoning? Evaluating Theory of Mind in LLMs for Open-Ended Responses [11.121931601655174]
  Theory of Mind (ToM) reasoning entails recognizing that other individuals possess their own intentions, emotions, and thoughts. Large language models (LLMs) excel in tasks such as summarization, question answering, and translation. Despite advancements, the extent to which LLMs truly understand ToM reasoning remains inadequately explored in open-ended scenarios.
  arXiv  Detail & Related papers  (2024-06-09T05:57:59Z)
• Systematic Biases in LLM Simulations of Debates [12.933509143906141]
  We study the limitations of Large Language Models in simulating human interactions.<n>Our findings indicate a tendency for LLM agents to conform to the model's inherent social biases.<n>These results underscore the need for further research to develop methods that help agents overcome these biases.
  arXiv  Detail & Related papers  (2024-02-06T14:51:55Z)
• Deception Abilities Emerged in Large Language Models [0.0]
  Large language models (LLMs) are currently at the forefront of intertwining artificial intelligence (AI) systems with human communication and everyday life. This study reveals that such strategies emerged in state-of-the-art LLMs, such as GPT-4, but were non-existent in earlier LLMs. We conduct a series of experiments showing that state-of-the-art LLMs are able to understand and induce false beliefs in other agents.
  arXiv  Detail & Related papers  (2023-07-31T09:27:01Z)

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.