Do LLMs Build World Representations? Probing Through the Lens of State Abstraction

Do LLMs Build World Representations? Probing Through the Lens of State Abstraction

Z. Li, Y. Cao, and J. C.K. Cheung. Conference on Neural Information Processing Systems (NeurIPS), 2024

Identifying and Addressing Delusions for Target-Directed Decision-Making

M. Zhao, T. Sylvain, D. Precup, and Y. Bengio. Workshop at Conference on Neural Information Processing System (NeurIPS), 2024

Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models

S. Mahdavi, R. Aoki, K. Tang, and Y. Cao. Conference on Neural Information Processing System (NeurIPS), 2024

Jump Starting Bandits with LLM-Generated Prior Knowledge

P. A. Alamdari, Y. Cao, and K. Wilson. Conference on Empirical Methods in Natural Language Processing, 2024