Zero-shot NLG evaluation through Pairware Comparisons with LLMs.

Adian Liusie Potsawee Manakul Mark J. F. Gales

Published in: CoRR (2023)

Keyphrases

comparative evaluation
natural language generation
real time
evaluation criteria
evaluation process
database
databases
artificial intelligence
natural language
hidden markov models
empirical evaluation
gold standard
quantitative evaluation
text generation