From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs
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…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
