Semantic entropy improves uncertainty estimation in natural language generation by incorporating semantic equivalences, outperforming standard entropy baselines on predicting model accuracy for question answering.
Additionally, we investigate, why the semantic entropy underperforms the length-normalised entropy at high temperatures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Semantic entropy improves uncertainty estimation in natural language generation by incorporating semantic equivalences, outperforming standard entropy baselines on predicting model accuracy for question answering.