Content generation conditioning on users's 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, Read-Ctrl 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 Read-Ctrl'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.

翻译：基于用户可读性的内容生成是个性化应用的重要方向。在大语言模型（LLM）时代，基于LLM的可读性控制文本生成变得日益重要。本文提出一种名为“可读性控制指令学习（ReadCtrl）”的新方法，旨在通过指令微调使LLM能够适应用户的可读性水平。与传统方法主要关注将可读性粗略划分为高、中、低或专家与大众等级别且效果有限不同，ReadCtrl引入了一个动态框架，使LLM能够在多种（近乎连续的）复杂度级别上生成内容，从而增强其在不同应用场景中的普适性。实验结果表明，ReadCtrl-Mistral-7B模型在人类评估中以52.1%:35.7%的胜率显著优于GPT-4和Claude-3等强基线模型。此外，ReadCtrl在自动评估中也展现出显著提升，具体体现在更优的可读性指标（如FOG、FKGL）和生成质量指标（如BLEU、SARI、SummaC-Factuality、UniEval-Consistency与Coherence）。这些结果证明了ReadCtrl在生成高质量、语境适配且精准匹配目标可读性水平的输出方面具有卓越效能与稳定性，标志着基于LLM的个性化内容生成领域取得了重要进展。