4 papers
Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People
Gabriel Grand, Valerio Pepe, Jacob Andreas +1
Many emerging applications of AI--from scientific discovery to medical diagnosis--require agents to seek information strategically: forming hypotheses, asking targeted questions, a…
Self-Steering Language Models
Gabriel Grand, Joshua B. Tenenbaum, Vikash K. Mansinghka +2
While test-time reasoning enables language models (LMs) to tackle complex tasks, searching or planning in natural language can be slow, costly, and error-prone. But even when LMs s…
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…
Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo
João Loula, Benjamin LeBrun, Li Du +12
A wide range of LM applications require generating text that conforms to syntactic or semantic constraints. Imposing such constraints can be naturally framed as probabilistic condi…