Less is more: instructed text simplification for people with aphasia

Background Patients with aphasia experience significant difficulties in reading and comprehending texts. Nevertheless, text-based activities constitute a substantial part of speech therapy programs for these patients. However, adapting textual material to patients’ linguistic and cognitive abilities presents a clinical challenge: texts must be engaging and personally relevant, yet their adaptation is time-consuming and labor-intensive. To address this issue, we have developed a methodology for the automatic simplification of texts for speech therapy in individuals with aphasia.Aims The aim of this study is to investigate the effectiveness of using Large Language Models (LLMs) for multilevel text simplification for patients with aphasia.Methods A parallel corpus consisting of 134 texts divided into 1010 sentences in Russian was prepared. Using guidelines developed by speech-language pathologists (SLPs) specializing in complex motor aphasia, eight Russian-speaking annotators generated three simplified versions for each original sentence, corresponding to three levels of disease severity. Our designed multi-tiered instructions and a sample comprising 100 original-to-simplified text pairs were used in a few-shot prompting strategy applied to four LLMs, which were then tasked with simplifying the texts.Outcomes and Results Models were evaluated using (1) linguistic complexity metrics and (2) BERTScore for semantic similarity. The top LLM’s output was clinically validated with 12 complex motor aphasia patients. Patients read six texts (three auto-simplified, three manual), then answered questions or retold stories. Automated texts scored slightly higher in perceived interest but lower in subjective “easiness” versus manual versions.Conclusions Findings indicate that few-shot-prompted automated simplification effectively adapts texts for complex motor aphasia patients. Simplified texts matched traditional therapy materials in linguistic complexity and retained strong semantic fidelity to their sources. While marginally less comprehensible than manual simplifications, patients rated them as more engaging.