Investigating the Effects of Zero-Shot Chain-of-Thought on Empathetic Dialogue Generation
Abstract
This study investigates the effectiveness of the Zero-shot Chain-of-Thought (CoT) approach, specifically the "Let's think step by step.'', in boosting the empathetic reasoning capabilities of Large Language Models (LLMs). Our experiments, however, reveal that Zero-shot CoT does not sufficiently enhance the empathetic reasoning of LLMs as compared to Zero-shot In-Context Learning (ICL), according to a variety of performance metrics. Importantly, we discovered that the perspective-taking prompting method, or ``\textit{Let's put speaker into interlocutor's shoes.}'', surpasses the performance of Zero-shot CoT, especially in terms of emotion and intent accuracy, with an improvement of 21\% and 7\% respectively. The source code will be released after publication.
Cite
Text
Lee et al. "Investigating the Effects of Zero-Shot Chain-of-Thought on Empathetic Dialogue Generation." NeurIPS 2023 Workshops: Instruction, 2023.Markdown
[Lee et al. "Investigating the Effects of Zero-Shot Chain-of-Thought on Empathetic Dialogue Generation." NeurIPS 2023 Workshops: Instruction, 2023.](https://mlanthology.org/neuripsw/2023/lee2023neuripsw-investigating/)BibTeX
@inproceedings{lee2023neuripsw-investigating,
title = {{Investigating the Effects of Zero-Shot Chain-of-Thought on Empathetic Dialogue Generation}},
author = {Lee, Young-Jun and Lee, Dokyong and Im, Jihui and Sung, Joo Won and Choi, Ho-Jin},
booktitle = {NeurIPS 2023 Workshops: Instruction},
year = {2023},
url = {https://mlanthology.org/neuripsw/2023/lee2023neuripsw-investigating/}
}