GPT-3.5 and GPT-4 can generate and evaluate turn-level commonsense dialogue expansions guided by ATOMIC relation definitions, with GPT-4 achieving the highest reranking accuracy.
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
-
Commonsense Generation and Evaluation for Dialogue Systems using Large Language Models
GPT-3.5 and GPT-4 can generate and evaluate turn-level commonsense dialogue expansions guided by ATOMIC relation definitions, with GPT-4 achieving the highest reranking accuracy.