沟通就是一切：通过多LLM通信构建说服数据集
Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication
AI总结：
针对LLMs生成说服性对话时存在的流畅性和复杂性问题，本文提出多LLM通信框架，可自动生成高质量多样化说服性数据，在自然性、多样性及说服策略运用上表现优异且能泛化到新语境，推动相关领域研究。
摘要：
大型语言模型（LLMs）在生成说服性对话方面已展现出熟练度，但对其输出的流畅性和复杂性的担忧依然存在。本文提出一种多LLM通信框架，旨在自动增强说服性数据的生成。该框架能在最少人工监督下高效生成高质量、多样化的语言内容。通过广泛评估，我们证明生成的数据在自然性、语言多样性和说服策略运用上表现优异，即使在涉及社会禁忌的复杂场景中也是如此。该框架还被证明能很好地泛化到新语境中。我们的结果凸显了该框架在显著推进说服性沟通相关的计算科学和社会科学领域研究方面的潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
