A new style-discrimination benchmark for personalized text generation shows ensemble metrics give only a marginal, possibly test-fitted, edge over the best single judge.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Evaluating Style-Personalized Text Generation: Challenges and Directions
A new style-discrimination benchmark for personalized text generation shows ensemble metrics give only a marginal, possibly test-fitted, edge over the best single judge.