SEPs approximate semantic entropy from single-generation hidden states to enable cheap and robust hallucination detection in LLMs.
Classification and regression trees.Wiley interdisciplinary reviews: data mining and knowledge discovery, 2011
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
SEPs approximate semantic entropy from single-generation hidden states to enable cheap and robust hallucination detection in LLMs.