Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
Potemkin Understanding in Large Language Models
Marina Mancoridis, Bec Weeks, Keyon Vafa +1
Large language models (LLMs) are regularly evaluated using benchmark datasets. But what justifies making inferences about an LLM's capabilities based on its answers to a curated se…
cs.CL2024
Evaluating the World Model Implicit in a Generative Model
Keyon Vafa, Justin Y. Chen, Ashesh Rambachan +2
Recent work suggests that large language models may implicitly learn world models. How should we assess this possibility? We formalize this question for the case where the underlyi…