Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements
This work addresses the problem of building more helpful AI for social interactions, but it is incremental as it builds on existing LLM capabilities.
The paper tackled empathetic response generation by investigating large language models (LLMs) and proposing three improvement methods, achieving state-of-the-art performance in automatic and human evaluations.
Empathetic dialogue is an indispensable part of building harmonious social relationships and contributes to the development of a helpful AI. Previous approaches are mainly based on fine small-scale language models. With the advent of ChatGPT, the application effect of large language models (LLMs) in this field has attracted great attention. This work empirically investigates the performance of LLMs in generating empathetic responses and proposes three improvement methods of semantically similar in-context learning, two-stage interactive generation, and combination with the knowledge base. Extensive experiments show that LLMs can significantly benefit from our proposed methods and is able to achieve state-of-the-art performance in both automatic and human evaluations. Additionally, we explore the possibility of GPT-4 simulating human evaluators.