paper-with-me

Papers

ReadCtrl: Personalizing text generation with readability-controlled instruction learning

2024-06-13 · Hieu Tran, Zonghai Yao, Lingxi Li, Hong Yu

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.

📄 PDF Abstract BibTeX arXiv:2406.09205

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Attention 설명 없음

Similar Papers 제목 키워드 기반

MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning

2025-07-10 · Hieu Tran, Zonghai Yao, Won Seok Jang, Sharmin Sultana 외 arxiv

Generative AI has demonstrated strong potential in healthcare, from clinical decision support to patient-facing chatbots that improve outcomes. A critical challenge for deployment is effective human-AI communication, whe…

Text Generation

Is it Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Models

2023-09-22 · Asma Farajidizaji, Vatsal Raina, Mark Gales

Text simplification is a common task where the text is adapted to make it easier to understand. Similarly, text elaboration can make a passage more sophisticated, offering a method to control the complexity of reading co…

Language ModellingReading ComprehensionText Simplification

Can LLMs Control Readability? A Multi-Dimensional Evaluation Framework for CEFR-Controlled Arabic Generation

2026-06-20 · Nour Rabih, Chatrine Qwaider, Ted Briscoe arxiv

While Large Language Models (LLMs) can generate fluent Arabic text, their ability to reliably control readability levels remains unclear. We propose a multi-dimensional evaluation framework for Common European Framework …

Text Generation

German4All -- A Dataset and Model for Readability-Controlled Paraphrasing in German

2025-08-25 · Miriam Anschütz, Thanh Mai Pham, Eslam Nasrallah, Maximilian Müller 외 arxiv

The ability to paraphrase texts across different complexity levels is essential for creating accessible texts that can be tailored toward diverse reader groups. Thus, we introduce German4All, the first large-scale German…

Text Simplification

Mathematics Teachers Interactions with a Multi-Agent System for Personalized Problem Generation

2026-04-13 · Candace Walkington, Theodora Beauchamp, Fareya Ikram, Merve Koçyiğit Gürbüz 외 arxiv

Large language models can increasingly adapt educational tasks to learners characteristics. In the present study, we examine a multi-agent teacher-in-the-loop system for personalizing middle school math problems. The tea…