<ul><li>Pre-trained large language models (LLMs) can effectively model data generated by Hidden Markov Models (HMMs) via in-context learning.</li><li>LLMs achieve predictive accuracy approaching the theoretical optimum on a diverse set of synthetic HMMs.</li><li>Novel scaling trends influenced by HMM properties were uncovered, along with practical guidelines for using in-context learning as a diagnostic tool for complex data.</li><li>In real-world animal decision-making tasks, in-context learning achieves competitive performance with models designed by human experts, showcasing its potential as a powerful tool for uncovering hidden structure in complex scientific data.</li></ul>

Pre-trained Large Language Models Learn Hidden Markov Models In-context

Discover more