Heads, Tails, and AI Fails: LLMs, Randomness, and Human Judgments

arXiv:2406.00092v2 Announce Type: replace Abstract: Randomness is central to human cognition and to many applications in which large language models are deployed, yet probabilistic token generation does not imply that LLMs can produce unbiased random sequences. We study how contemporary LLMs generate binary random sequences using the classic behavioral-science paradigm of simulated coin flips. Across single flips, 20-flip sequences, n-gram statistics, run lengths, alternation rates, and next-flip predictability, we compare model outputs to both true Bernoulli baselines and human data from prior work. We find that LLMs reproduce several canonical human randomness biases, including over-alternation, aversion to long runs, and first-flip biases, but often amplify them or introduce model-specific distortions. Increasing temperature reduces some rigid patterns but does not eliminate systematic structure. We further investigate over-alternation through prompt-framing experiments, continuation tests, corpus searches, and residual-stream probes, finding evidence that this bias is not explained by direct memorization or tokenization alone. These results show that LLMs are unreliable generators of randomness and imperfect simulators of human randomness judgments, with implications for applications requiring stochasticity, fair sampling, or behavioral simulation.

Abstract:Randomness is central to human cognition and to many applications in which large language models are deployed, yet probabilistic token generation does not imply that LLMs can produce unbiased random sequences. We study how contemporary LLMs generate binary random sequences using the classic behavioral-science paradigm of simulated coin flips. Across single flips, 20-flip sequences, n-gram statistics, run lengths, alternation rates, and next-flip predictability, we compare model outputs to both true Bernoulli baselines and human data from prior work. We find that LLMs reproduce several canonical human randomness biases, including over-alternation, aversion to long runs, and first-flip biases, but often amplify them or introduce model-specific distortions. Increasing temperature reduces some rigid patterns but does not eliminate systematic structure. We further investigate over-alternation through prompt-framing experiments, continuation tests, corpus searches, and residual-stream probes, finding evidence that this bias is not explained by direct memorization or tokenization alone. These results show that LLMs are unreliable generators of randomness and imperfect simulators of human randomness judgments, with implications for applications requiring stochasticity, fair sampling, or behavioral simulation.

Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2406.00092 [cs.AI]

(or arXiv:2406.00092v2 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2406.00092 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Heads, Tails, and AI Fails: LLMs, Randomness, and Human Judgments

Related coverage