A dual-refinement method (DRE) that uses a contrastively trained small language model to guide and rescale an LLM's dialogue quality scores achieves higher correlation with human ratings than LLM-only baselines on three datasets.
In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6676–6689
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DRE: An Effective Dual-Refined Method for Integrating Small and Large Language Models in Open-Domain Dialogue Evaluation
A dual-refinement method (DRE) that uses a contrastively trained small language model to guide and rescale an LLM's dialogue quality scores achieves higher correlation with human ratings than LLM-only baselines on three datasets.