Article

The Lie Awareness Spectrum: How Large Language Models Recognize, Rationalize, and Refuse Deception

2026-07-22

Abstract excerpt

<title>Abstract</title> <p> As large language models (LLMs) become embedded in high-stakes decision-making, understanding their capacity for deception—and awareness of it—is critical. We conducted a systematic empirical study comparing GPT-5.4, Claude 4.6 Sonnet, and Gemini 3.1 Pro across scenarios requiring truth manipulation, revealing a previously uncharacterized "Lie Awareness Spectrum" (L0–L5) from statisti...

Topics

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

Identifiers and source

Literature Corpus work: 26ae3285-318e-5736-959a-2eb074c20a25
DOI: 10.21203/rs.3.rs-10422338/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

The Lie Awareness Spectrum: How Large Language Models Recognize, Rationalize, and Refuse DeceptionDOI 10.21203/rs.3.rs-10422338/v1Read

The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-MakingSemantic proximity Read

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

Can LLMs Get High? A Dual-Metric Framework for Evaluating Psychedelic Simulation and Safety in Large Language ModelsSemantic proximity Read

The boredom trap: How LLMs are draining entropy from the way we communicateSemantic proximity Read

Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-MakingSemantic proximity Read

A ChatGPT-Generated Taxonomy of Risky Real-Life SituationsSemantic proximity Read

A Moral Turing Test to assess How Subjective Belief and Objective Source Affect Detection and Agreement with LLM JudgmentsSemantic proximity Read

Reading Between the Lines: LLMs Match or Exceed Human Empathic Accuracy Using Text AloneSemantic proximity Read

When Do LLMs Say “Some”? An Investigation of Scalar Implicature and Politeness Mitigation in Large Language ModelsSemantic proximity Read

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

Cognitive dissonance in large language models is neither cognitive nor dissonantSemantic proximity Read

Generative AI are More Truth-Biased than Humans: A Replication and Extension of Core Truth-Default Theory PrinciplesSemantic proximity Read