Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

arXiv:2601.05905v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual perturbations. Existing evaluations largely rely on point-wise confidence like Self-Consistency, which can mask brittle belief. We show that even facts answered with perfect self-consistency can rapidly collapse under mild contextual interference. To