Evaluation of Multilingual LLMs Personalized Text Generation Capabilities Targeting Groups and Social-Media Platforms
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 7 Jan 2026.
Builds on
13 of 23 references.
References · 13
- 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
- 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
- 2023Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvaturecited by 278
- 2024Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textcited by 255
- 2023Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformationcited by 51
- 2025ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generationcited by 26
- 2024Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generationcited by 20
- 2024Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluationcited by 15
- 2024METAL: Towards Multilingual Meta-Evaluationcited by 14
- 2025Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectorscited by 8
- 2025PREF: Reference-Free Evaluation of Personalised Text Generation in LLMscited by 5
- 2025Tailored untruths: How personalisation challenges LLM safeguardscited by 2
Built on by
Not cited yet.