用GPT生成总统演讲，风格差异明显。
GPT as ghostwriter at the White House
- 对比特朗普到奥巴马的国情咨文与GPT生成文本。
- GPT多用'我们'、名词和逗号，句子更长但动词少。
- 生成文本语气中性偏积极，适合做风格分析参考。
近期多个大语言模型（LLMs）已展现根据用户请求生成文本的能力。本研究聚焦于分析名为ChatGPT 3.5的LLM的写作风格，将其生成内容与美国历任总统的国情咨文进行对比。研究选取里根至奥巴马时期的国情咨文，并与由ChatGPT自动生成的文本进行比较。结果显示，ChatGPT倾向于过度使用代词'we'以及名词和逗号；生成文本动词较少，平均句长更长。即使设定特定风格，其生成内容仍与目标作者的文本存在显著差异。此外，生成文本采用中性语气，主要表达正面情感及象征性词汇（如自由、国家）。最终发现，GPT生成的文本在风格特征上明显区别于真实的总统演讲。
原文摘要 · Abstract (English)
Recently several large language models (LLMs) have demonstrated their capability to generate a message in response to a user request. Such scientific breakthroughs promote new perspectives but also some fears. The main focus of this study is to analyze the written style of one LLM called ChatGPT 3.5 by comparing its generated messages with those of the recent US presidents. To achieve this objective, we compare the State of the Union addresses written by Reagan to Obama with those automatically produced by ChatGPT. We found that ChatGPT tends to overuse the lemma "we" as well as nouns and commas. On the other hand, the generated speeches employ less verbs and include, in mean, longer sentences. Even when imposing a given style to ChatGPT, the resulting speech remains distinct from messages written by the target author. Moreover, ChatGPT opts for a neutral tone with mainly positive emotional expressions and symbolic terms (e.g., freedom, nation). Finally, we show that the GPT's style exposes distinct features compared to real presidential addresses.
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。