用大模型改写演讲稿，发现其操控语言风格来增强说服力
The Anatomy of Speech Persuasion: Linguistic Shifts in LLM-Modified Speeches
- 用GPT-4o修改演讲稿，分析修辞与话语标记的语义变化
- 模型通过调整情绪词汇和疑问感叹句提升修辞效果
- 揭示大模型非人类式说服策略，适合研究生成文本机制
本研究探讨大语言模型如何理解公共演讲中的说服力，基于法国3MT竞赛中博士生演讲稿（3MT French dataset），使用GPT-4o对原文进行说服力增强或削弱。提出一种新方法与可解释的文本特征集，融合修辞手法与话语标记。分析原始与生成文本间的语言变化，结果表明：GPT-4o并非以类人方式优化说服力，而是系统性地调整语言风格；尤其通过操控情绪词库与句法结构（如疑问句、感叹句）强化修辞效果。
原文摘要 · Abstract (English)
This study examines how large language models understand the concept of persuasiveness in public speaking by modifying speech transcripts from PhD candidates in the "Ma These en 180 Secondes" competition, using the 3MT French dataset. Our contributions include a novel methodology and an interpretable textual feature set integrating rhetorical devices and discourse markers. We prompt GPT-4o to enhance or diminish persuasiveness and analyze linguistic shifts between original and generated speech in terms of the new features. Results indicate that GPT-4o applies systematic stylistic modifications rather than optimizing persuasiveness in a human-like manner. Notably, it manipulates emotional lexicon and syntactic structures (such as interrogative and exclamatory clauses) to amplify rhetorical impact.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。