An NLG evaluator that scores text by softmax-weighted comparisons against five LLM-generated synthetic summaries matches pairwise evaluator performance on SummEval, TopicalChat, and HANNA.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Direct-Scoring NLG Evaluators Can Use Pairwise Comparisons Too
An NLG evaluator that scores text by softmax-weighted comparisons against five LLM-generated synthetic summaries matches pairwise evaluator performance on SummEval, TopicalChat, and HANNA.