JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory Paper • 2509.22888 • Published Sep 26, 2025 • 1
Rhetorical Questions in LLM Representations: A Linear Probing Study Paper • 2604.14128 • Published Apr 21
Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering Paper • 2508.04945 • Published Jan 25
Hallucination in World Models is Predictable and Preventable Paper • 2606.27326 • Published 6 days ago • 8
JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory Paper • 2509.22888 • Published Sep 26, 2025 • 1