多语言大语言模型针对特定群体和社会媒体平台的个性化文本生成能力评估
Evaluation of Multilingual LLMs Personalized Text Generation Capabilities Targeting Groups and Social-Media Platforms
AI总结：
本研究评估多语言大语言模型在不同语言中针对特定群体和社会媒体平台的个性化文本生成能力，发现个性化对文本可检测性的影响因语言而异，尤其在英语中影响显著。
摘要：
大型语言模型生成多语言连贯文本的能力在近年来持续增强，这引发了对其潜在滥用的担忧。先前的研究表明，它们可以被滥用于生成多语言的个性化虚假信息。此外，还观察到个性化会降低机器生成文本的可检测性；然而，这种现象仅在英语中被研究过。在本工作中，我们跨10种语言考察这一现象，不仅关注个性化能力的潜在滥用，还关注其可能带来的好处。总体而言，我们覆盖了1080种不同的个性化方面组合，在提示中生成文本，由16种不同的语言模型生成（总计17280篇文本）。我们的结果表明，在针对人口群体和针对社交媒体平台时，生成文本的个性化质量在不同语言中存在差异。针对平台的个性化对生成文本的可检测性影响更大，尤其是在英语中，个性化质量最高。
英文摘要：
Capabilities of large language models to generate multilingual coherent text have continuously enhanced in recent years, which opens concerns about their potential misuse. Previous research has shown that they can be misused for generation of personalized disinformation in multiple languages. It has also been observed that personalization negatively affects detectability of machine-generated texts; however, this has been studied in the English language only. In this work, we examine this phenomenon across 10 languages, while we focus not only on potential misuse of personalization capabilities, but also on potential benefits they offer. Overall, we cover 1080 combinations of various personalization aspects in the prompts, for which the texts are generated by 16 distinct language models (17,280 texts in total). Our results indicate that there are differences in personalization quality of the generated texts when targeting demographic groups and when targeting social-media platforms across languages. Personalization towards platforms affects detectability of the generated texts in a higher scale, especially in English, where the personalization quality is the highest.
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。
