Article

Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM Agents

2026-08-14

Abstract excerpt

An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present PsyAgentBench, a benchmark that re-runs classic psychology experiments on LLM agents under a factorial design built to separate these: each paradigm is run with the paradigm explicitly labeled in the prompt (named) or framed as a routine task (blind), and on the liter...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 91039257-e0d6-566f-b7ee-f410b66c9208
DOI: 10.20944/preprints202608.0971.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM AgentsDOI 10.20944/preprints202608.0971.v1Read

AI-mediated contamination in online research: Taxonomy, risk gradient, and recommendationsSemantic proximity Read

Artificial-Intelligence-Mediated Contamination in Online Research: Taxonomy, Risk Gradient, and RecommendationsSemantic proximity Read

Mental AI: Post-Deployment Criterion Endogeneity in the Causal Loop of Human Mental LifeSemantic proximity Read

Can AI Be Morally Wise? Evidence of a Systematic Alignment Artifact from a Validated Human BaselineSemantic proximity Read

Simulating Ideological Deadlock: Persona Stability and Conflict Resolution in LLM-Based Multi-Agent FrameworksSemantic proximity Read

Human Psychology in the Age of AI: What Changes and What Doesn’tSemantic proximity Read

Homo Silicus is Hyper-Rational: Why LLM Agents Fail to Replicate Attention-Driven TradingSemantic proximity Read

The Lie Awareness Spectrum: How Large Language Models Recognize, Rationalize, and Refuse DeceptionSemantic proximity Read

Computational Dysfunction: Diagnosing Emergent Psychopathologies in Advanced Language Models for Aligned SystemsSemantic proximity Read

Lighting the Dark Side of the Model: Psychometric Probing of Dark Triad Traits in LLMsSemantic proximity Read

Successful Automatic Model Discovery Can Produce False MechanismsSemantic proximity Read