Pre-trained Large Language Models Learn Hidden Markov Models In-context
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917431482515456 |
|---|---|
| author | Dai, Yijia Gao, Zhaolin Sattar, Yahya Dean, Sarah Sun, Jennifer J. |
| author_facet | Dai, Yijia Gao, Zhaolin Sattar, Yahya Dean, Sarah Sun, Jennifer J. |
| contents | Hidden Markov Models (HMMs) are foundational tools for modeling sequential data with latent Markovian structure, yet fitting them to real-world data remains computationally challenging. In this work, we show that pre-trained large language models (LLMs) can effectively model data generated by HMMs via in-context learning (ICL)$\unicode{x2013}$their ability to infer patterns from examples within a prompt. On a diverse set of synthetic HMMs, LLMs achieve predictive accuracy approaching the theoretical optimum. We uncover novel scaling trends influenced by HMM properties, and offer theoretical conjectures for these empirical observations. We also provide practical guidelines for scientists on using ICL as a diagnostic tool for complex data. On real-world animal decision-making tasks, ICL achieves competitive performance with models designed by human experts. To our knowledge, this is the first demonstration that ICL can learn and predict HMM-generated sequences$\unicode{x2013}$an advance that deepens our understanding of in-context learning in LLMs and establishes its potential as a powerful tool for uncovering hidden structure in complex scientific data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07298 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pre-trained Large Language Models Learn Hidden Markov Models In-context Dai, Yijia Gao, Zhaolin Sattar, Yahya Dean, Sarah Sun, Jennifer J. Machine Learning Artificial Intelligence Hidden Markov Models (HMMs) are foundational tools for modeling sequential data with latent Markovian structure, yet fitting them to real-world data remains computationally challenging. In this work, we show that pre-trained large language models (LLMs) can effectively model data generated by HMMs via in-context learning (ICL)$\unicode{x2013}$their ability to infer patterns from examples within a prompt. On a diverse set of synthetic HMMs, LLMs achieve predictive accuracy approaching the theoretical optimum. We uncover novel scaling trends influenced by HMM properties, and offer theoretical conjectures for these empirical observations. We also provide practical guidelines for scientists on using ICL as a diagnostic tool for complex data. On real-world animal decision-making tasks, ICL achieves competitive performance with models designed by human experts. To our knowledge, this is the first demonstration that ICL can learn and predict HMM-generated sequences$\unicode{x2013}$an advance that deepens our understanding of in-context learning in LLMs and establishes its potential as a powerful tool for uncovering hidden structure in complex scientific data. |
| title | Pre-trained Large Language Models Learn Hidden Markov Models In-context |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.07298 |