Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication
This work addresses the need for high-quality persuasive data in computational and social science research, though it appears incremental as it builds on existing LLM capabilities.
The paper tackled the problem of generating persuasive dialogue data by introducing a multi-LLM communication framework, resulting in data that excels in naturalness, linguistic diversity, and strategic persuasion in complex scenarios like social taboos.
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.