EmPO: Theory-Driven Dataset Construction for Empathetic Response Generation through Preference Optimization

Empathetic response generation is a desirable aspect of conversational agents, crucial for facilitating engaging and emotionally intelligent multi-turn conversations between humans and machines. Leveraging large language models for this task has shown promising results, yet challenges persist in ensuring both the empathetic quality of the responses and retention of the generalization performance of the models. In this paper, we propose a novel approach where we construct theory-driven preference datasets and use them to align LLMs with preference optimization algorithms to address these challenges. To measure empathetic response generation, we employ the EmpatheticDialogues dataset, assessing empathy with the diff-EPITOME and BERTscore metrics, and evaluate the generalization performance on the MMLU benchmark. We make all datasets, source code, and models publicly available.