演讲说服力的解剖：LLM修改演讲中的语言变化
The Anatomy of Speech Persuasion: Linguistic Shifts in LLM-Modified Speeches
AI总结：
本研究通过GPT-4o修改3MT法语数据集中的演讲文稿，分析语言变化，发现其采用系统性风格修改而非人类式优化，并操纵情感词汇和句法结构以增强修辞效果。
摘要：
本研究探讨了大语言模型如何理解公共演讲中的说服力概念，方法是对“Ma These en 180 Secondes”竞赛中博士候选人的演讲文稿进行修改，使用了3MT法语数据集。我们的贡献包括一种新颖的方法论和一个可解释的文本特征集，该特征集整合了修辞手法和话语标记。我们提示GPT-4o增强或削弱说服力，并基于新特征分析原始演讲与生成演讲之间的语言变化。结果表明，GPT-4o应用了系统性的风格修改，而非以类似人类的方式优化说服力。值得注意的是，它操纵情感词汇和句法结构（如疑问句和感叹句）以增强修辞效果。
英文摘要：
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.
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。
