A virtue-labeled lookup table maps coarse uncertainty tags to canned warnings or disclaimers; the only quantitative result is 50% tag accuracy on 20 author-written prompts, with trust improvements asserted but untested.
Dropout as a Bayesian approximation: Representing model uncertainty in deep learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Rule-Based Moral Principles for Explaining Uncertainty in Natural Language Generation
A virtue-labeled lookup table maps coarse uncertainty tags to canned warnings or disclaimers; the only quantitative result is 50% tag accuracy on 20 author-written prompts, with trust improvements asserted but untested.