Conditioning on Dialog Acts improves Empathy Style Transfer
Submission Type: Regular Long Paper
Submission Track: Discourse and Pragmatics
Submission Track 2: Dialogue and Interactive Systems
Keywords: empathy style transfer, text style transfer, empathy, GPT-4, large language models, dialog acts, pragmatics, prompt engineering, in-context learning, few-shot prompting
TL;DR: In empathy style transfer with large language models, conditioning few-shot examples on dialog acts improves style transfer strength and content preservation.
Abstract: We explore the role of dialog acts in style transfer, specifically empathy style transfer -- rewriting a sentence to make it more empathetic without changing its meaning. Specifically, we use two novel few-shot prompting strategies: target prompting, which only uses examples of the target style (unlike traditional prompting with source/target pairs), and dialog-act-conditioned prompting, which first estimates the dialog act of the source sentence and then makes it more empathetic using few-shot examples of the same dialog act. Our study yields two key findings: (1) Target prompting typically improves empathy more effectively while maintaining the same level of semantic similarity; (2) Dialog acts matter. Dialog-act-conditioned prompting enhances empathy while preserving both semantics and the dialog-act type. Different dialog acts benefit differently from different prompting methods, highlighting the need for further investigation of the role of dialog acts in style transfer.
Submission Number: 2201
Loading