@inproceedings{tran-etal-2025-readctrl,
    title = "{R}ead{C}trl: Personalizing text generation with readability-controlled instruction learning",
    author = "Tran, Hieu  and
      Yao, Zonghai  and
      Li, Lingxi  and
      Yu, Hong",
    editor = "Padmakumar, Vishakh  and
      Gero, Katy  and
      Wambsganss, Thiemo  and
      Sterman, Sarah  and
      Huang, Ting-Hao  and
      Zhou, David  and
      Chung, John",
    booktitle = "Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2025)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico, US",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.in2writing-1.3/",
    pages = "19--36",
    ISBN = "979-8-89176-239-8",
    abstract = "Content generation conditioning on users' readability is an important application for personalization. In an era of large language models (LLMs), readability-controlled text generation based on LLMs has become increasingly important. This paper introduces a novel methodology called ``Readability-Controlled Instruction Learning (ReadCtrl),'' which aims to instruction-tune LLMs to tailor users' readability levels. Unlike the traditional methods, which primarily focused on categorical readability adjustments{---}typically classified as high, medium, and low or expert and layperson levels{---}with limited success, ReadCtrl introduces a dynamic framework that enables LLMs to generate content at various (near continuous level) complexity levels, thereby enhancing their versatility across different applications. Our results show that the ReadCtrl-Mistral-7b models significantly outperformed strong baseline models such as GPT-4 and Claude-3, with a win rate of 52.1{\%}:35.7{\%} against GPT-4 in human evaluations. Furthermore, ReadCtrl has shown significant improvements in automatic evaluations, as evidenced by better readability metrics (e.g., FOG, FKGL) and generation quality metrics (e.g., BLEU, SARI, SummaC-Factuality, UniEval-Consistency and Coherence). These results underscore ReadCtrl{'}s effectiveness and tenacity in producing high-quality, contextually appropriate outputs that closely align with targeted readability levels, marking a significant advancement in personalized content generation using LLMs."
}