用大模型自动生成易读文本，助力认知障碍者平等获取信息
Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation
- 多任务学习联合训练摘要、简化与易读文本生成
- 基于ETR-fr数据集，多任务模型优于单任务基线
- 检索增强策略适配跨领域场景，LoRA微调在本领域表现最优
简化复杂文本对保障认知障碍群体的信息公平获取至关重要。现有的易读（ETR）倡议为神经多样性人群提供内容可访问性框架，但手动制作仍耗时费力。本文研究大语言模型（LLMs）在自动化生成ETR内容中的潜力。针对标注语料稀缺和ETR约束特殊的问题，提出一种多任务学习（MTL）方法，联合训练文本摘要、文本简化与ETR生成。探索两种策略：基于检索增强生成（RAG）的上下文学习，以及参数高效微调的MTL-LoRA。基于新构建的高质量数据集ETR-fr，使用Mistral-7B和LLaMA-3-8B进行实验，结果表明多任务设置在所有配置下均优于单任务基线。此外，RAG策略在跨领域场景中展现良好泛化能力，而MTL-LoRA在本领域配置中表现最佳。
原文摘要 · Abstract (English)
Simplifying complex texts is essential for ensuring equitable access to information, especially for individuals with cognitive impairments. The Easy-to-Read (ETR) initiative offers a framework for making content accessible to the neurodivergent population, but the manual creation of such texts remains time-consuming and resource-intensive. In this work, we investigate the potential of large language models (LLMs) to automate the generation of ETR content. To address the scarcity of aligned corpora and the specificity of ETR constraints, we propose a multi-task learning (MTL) approach that trains models jointly on text summarization, text simplification, and ETR generation. We explore two different strategies: multi-task retrieval-augmented generation (RAG) for in-context learning, and MTL-LoRA for parameter-efficient fine-tuning. Our experiments with Mistral-7B and LLaMA-3-8B, based on ETR-fr, a new high-quality dataset, demonstrate the benefits of multi-task setups over single-task baselines across all configurations. Moreover, results show that the RAG-based strategy enables generalization in out-of-domain settings, while MTL-LoRA outperforms all learning strategies within in-domain configurations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。