token-level-detection

UniProbe is a lightweight detector that uses graph-based multi-structural internal representations to identify hallucinated tokens in large vision-language models, reducing object hallucinations by up to 55% with minimal latency increase.

Reformulates token-level hallucination detection as a quickest change detection problem, establishing theoretical lower bounds on detection delay and showing that causal recurrent models achieve near-optimal performance, outperforming linear baselines.