Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916336497590272 |
|---|---|
| author | Qian, Yushan Zhang, Wei-Nan Liu, Ting |
| author_facet | Qian, Yushan Zhang, Wei-Nan Liu, Ting |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_05140 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements Qian, Yushan Zhang, Wei-Nan Liu, Ting Computation and Language Artificial Intelligence 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. |
| title | Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2310.05140 |