AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

When LLMs support public-facing or high-stakes workflows, missed fabrications can harm users and institutions, while false alarms consume limited human-review capacity. When no trusted context or reference document is available, we study two signals accessible through black-box model APIs: semantic entropy, which measures disagreement among sampled response meanings, and uncertainty derived from token log-probabilities. Their failure modes can be complementary: semantic entropy becomes uninformative when responses form one semantic cluster, while token uncertainty can miss consistently confide

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T05:32:15.665Z. This is not the publication date.