Communication Makes Perfect: Persuasion Dataset Construction via Multi-LLM Communication
Weicheng Ma, Hefan Zhang, Ivory Yang, Shiyu Ji, Joice Chen, Farnoosh Hashemi, Shubham Mohole, Ethan Gearey
Abstract
Large Language Models (LLMs) have shown proficiency in generating persuasive dialogue, yet concerns about the fluency and sophistication of their outputs persist. This paper presents a multi-LLM communication framework designed to enhance the generation of persuasive data automatically. This framework facilitates the efficient production of high-quality, diverse linguistic content with minimal human oversight. Through extensive evaluations, we demonstrate that the generated data excels in naturalness, linguistic diversity, and the strategic use of persuasion, even in complex scenarios involving social taboos. The framework also proves adept at generalizing across novel contexts. Our results highlight the framework’s potential to significantly advance research in both computational and social science domains concerning persuasive communication.
BibTeX
@inproceedings{ma-etal-2025-communication,
title = "Communication Makes Perfect: Persuasion Dataset Construction via Multi-{LLM} Communication",
author = "Ma, Weicheng and
Zhang, Hefan and
Yang, Ivory and
Ji, Shiyu and
Chen, Joice and
Hashemi, Farnoosh and
Mohole, Shubham and
Gearey, Ethan and
Macy, Michael and
Hassanpour, Saeed and
Vosoughi, Soroush",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.203/",
pages = "4017--4045",
ISBN = "979-8-89176-189-6"
}