Researchers propose a cross-model hidden-state probing framework in which an external observer can match or exceed a generator's self-detection of its own hallucination onsets
The work introduces an internal hidden-state framework for fine-grained, span-level hallucination detection that inspects layer-wise activation patterns to locate the onset and continuation tokens of hallucinations in large language model generations; experiments show substantial improvements in Precision-Recall AUC over random baselines despite extreme class imbalance, and it further proposes a cross-model detection framework in which one model observes the internal representations elicited by another model's generation, finding that an external observer can match or exceed the generator's self-detection of its own hallucination onsets, including when the observer is the smaller model.