When LLMs Manipulate: Measuring Behavioral, Social, and Temporal Effects

arXiv:2610.27573v1 Announce Type: new Abstract: Large language models (LLMs) can influence user trust and decision-making through subtle linguistic cues, yet the behavioral effects of manipulative outputs remain poorly quantified. We introduce a behavioral computing framework for measuring extit{behavioral vulnerability}, defined as users' susceptibility to manipulative AI responses. Building on DarkPatterns-LLM benchmark, we generate controlled manipulative stimuli using Manipulation Gradient Descent (MGD), targeting biases associated with authority, urgency, and social proof. We analyze participant responses using the Multi-Stakeholder Impact Assessment Network (MSIAN) to model cross-user influence and the Temporal Harm Propagation Model (THPM) to characterize the persistence of behavioral effects over time. In a study involving 120 participants, manipulative framing produced significant changes in trust calibration and compliance (p < 0.01), with effects also propagating across social contexts. These findings highlight the need to extend LLM safety evaluation beyond model outputs to measurable behavioral consequences and provide a computational framework for quantifying individual, social, and temporal risks arising from manipulative AI interactions.

Related

• Can I Take Another Dose? Evaluating LLM Decision-Making Under Temporal Uncertainty in OTC Dosing QA
• Mimicry without understanding: the origins of decision bias in large language models
• NICE: A Theory-Grounded Diagnostic Benchmark for Social Intelligence of LLMs
• Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles

Source: arXiv cs.AI | 2026-10-21