Pith. sign in

REVIEW 2 cited by

Do Large Language Models Exhibit Spontaneous Rational Deception?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.00285 v1 pith:ZG3W2WIV submitted 2025-03-31 cs.CL

classification cs.CL
keywords llmstheydeceivedeceptionmodelsreasoningbetterconditions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception. Do they also increasingly deceive spontaneously in situations where it could be considered rational to do so? This study evaluates spontaneous deception produced by LLMs in a preregistered experimental protocol using tools from signaling theory. A range of proprietary closed-source and open-source LLMs are evaluated using modified 2x2 games (in the style of Prisoner's Dilemma) augmented with a phase in which they can freely communicate to the other agent using unconstrained language. This setup creates an opportunity to deceive, in conditions that vary in how useful deception might be to an agent's rational self-interest. The results indicate that 1) all tested LLMs spontaneously misrepresent their actions in at least some conditions, 2) they are generally more likely to do so in situations in which deception would benefit them, and 3) models exhibiting better reasoning capacity overall tend to deceive at higher rates. Taken together, these results suggest a tradeoff between LLM reasoning capability and honesty. They also provide evidence of reasoning-like behavior in LLMs from a novel experimental configuration. Finally, they reveal certain contextual factors that affect whether LLMs will deceive or not. We discuss consequences for autonomous, human-facing systems driven by LLMs both now and as their reasoning capabilities continue to improve.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games

    cs.CY 2026-07 conditional novelty 6.5 of 10

    LLM commitment-breaking is mostly premeditated and game-dependent, and heterogeneous model groups produce persistent payoff gaps from incompatible announcement semantics.

  2. CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs

    cs.AI 2025-08 reject novelty 6.0 of 10

    CHBench fits Level-K and Poisson cognitive hierarchy models to LLM game play and uses the fitted reasoning level as a benchmark score.

Pith tools