Tag
This paper introduces Distributional Process Reward Models, using conditional optimal transport to calibrate PRMs for more accurate success probability estimates in inference-time scaling. It demonstrates improved calibration and downstream performance on mathematical reasoning benchmarks like MATH-500 and AIME.
This paper introduces SIVR (Sequential Internal Variance Representation), a supervised framework for detecting hallucinations in LLMs by analyzing token-wise and layer-wise variance patterns in hidden states without relying on strict architectural assumptions. The method aggregates full sequence variance features to learn temporal patterns of factual errors and demonstrates improved generalization with smaller training sets.
MIT researchers propose a framework for 'humble' AI in healthcare that encourages systems to express uncertainty and act as collaborative co-pilots rather than authoritative oracles.