Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation
This addresses the problem of time-consuming manual text simplification for individuals with cognitive impairments, though it is incremental as it builds on existing LLM and multi-task methods.
The paper tackles automating Easy-to-Read text generation for cognitive accessibility by proposing a multi-task learning approach with LLMs, achieving benefits over single-task baselines and showing generalization with RAG and in-domain gains with MTL-LoRA.
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.