2 papers
cs.CL2025
Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models
Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin +17
The ability to build and reason about models of the world is essential for situated language understanding. But evaluating world modeling capabilities in modern AI systems -- espec…
cs.CL2024
Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models
Daria Kryvosheieva, Roger Levy
Language models (LMs) are capable of acquiring elements of human-like syntactic knowledge. Targeted syntactic evaluation tests have been employed to measure how well they form gene…