Peter Clark

AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite

SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs

HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation

ArtifactLinker: Linking Scientific Artifacts for Automatic SOTA Discovery

Language Modeling by Language Models

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise

DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question-Answering

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs