TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection

ArXi:2606.01033v1 Announce Type: new When a language model hallucinates, the final answer is wrong, but the mistake is not necessarily invisible inside the model. Different internal pathways may remain uncertain, disagree in how quickly they sharpen, or commit to competing continuations before the output is produced. We