ReadCtrl: Personalizing text generation with readability-controlled instruction learning

TL;DR

ReadCtrl introduces a dynamic instruction-tuning method for LLMs to generate personalized content at various readability levels, outperforming baseline models in human and automatic evaluations.

Contribution

This paper presents a novel Readability-Controlled Instruction Learning framework that enables LLMs to produce content at near continuous readability levels, improving personalization and versatility.

Findings

ReadCtrl-Mistral-7B outperformed GPT-4 and Claude-3 in human evaluations.

Significant improvements in readability and quality metrics over baselines.

Effective generation of contextually appropriate content at targeted readability levels.

Abstract

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.