Idan Szpektor

ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs

Unblocking Fine-Grained Evaluation of Detailed Captions: An Explaining AutoRater and Critic-and-Revise Pipeline

3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model

Inside-Out: Hidden Factual Knowledge in LLMs

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance

Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

Distinguishing Ignorance from Error in LLM Hallucinations