Kishore Chalakkal Varghese

Predicting and Controlling Hallucination Onset in Large Language Models: A Belief-State Framework for Prospective Risk, Optimal Intervention, and Recoverability

Hallucination mitigation in large language models (LLMs) is commonly approached through post-hoc factuality checks, uncertainty scores, token- or span-level detectors, or abstention rules. These methods are valuable but do not fully specify the sequential decision problem that ar...