Eliciting the Priors of Large Language Models using Iterated In-Context Learning
Zhu, Jian-Qiao, Griffiths, Thomas L.
–arXiv.org Artificial Intelligence
As Large Language Models (LLMs) are increasingly deployed in real-world settings, understanding the knowledge they implicitly use when making decisions is critical. One way to capture this knowledge is in the form of Bayesian prior distributions. We develop a prompt-based workflow for eliciting prior distributions from LLMs. Our approach is based on iterated learning, a Markov chain Monte Carlo method in which successive inferences are chained in a way that supports sampling from the prior distribution. We validated our method in settings where iterated learning has previously been used to estimate the priors of human participants -- causal learning, proportion estimation, and predicting everyday quantities. We found that priors elicited from GPT-4 qualitatively align with human priors in these settings. We then used the same method to elicit priors from GPT-4 for a variety of speculative events, such as the timing of the development of superhuman AI.
arXiv.org Artificial Intelligence
Jun-3-2024
- Country:
- Europe > United Kingdom
- England (0.14)
- North America > United States (0.67)
- Europe > United Kingdom
- Genre:
- Research Report > New Finding (0.67)
- Industry:
- Energy (0.95)
- Government (0.93)
- Health & Medicine (1.00)
- Technology: