Recent surge in the accessibility of large language models (LLMs) to the general population can lead to untrackable use of such models for medical-related recommendations. Language generation via LLMs models has two key problems: firstly, they are prone to hallucination and therefore, for any medical purpose they require scientific and factual grounding; secondly, LLMs pose tremendous challenge to computational resources due to their gigantic model size. In this work, we introduce pRAGe, a Pipeline for Retrieval Augmented Generation and Evaluation of medical paraphrases generation using Small Language Models (SLM). We study the effectiveness of SLMs and the impact of external knowledge base for medical paraphrase generation in French.

This article presents a method extending an existing French corpus of paraphrases of medical terms ANONYMOUS with new data from Web archives created during the Covid-19 pandemic. Our method semi-automatically detects new terms and paraphrase markers introducing paraphrases from these Web archives, followed by a manual annotation step to identify paraphrases and their lexical and semantic properties. The extended large corpus LARGEMED could be used for automatic medical text simplification for patients and their families. To automatise data collection, we propose two experiments. The first experiment uses the new LARGEMED dataset to train a binary classifier aiming to detect new sentences containing possible paraphrases. The second experiment aims to use correct paraphrases to train a model for paraphrase generation, by adapting T5 Language Model to the paraphrase generation task using an adversarial algorithm.

Les textes médicaux sont difficiles à comprendre pour le grand public à cause des termes de spécialité. Ces notions médicales ont besoin d’être reformulées en utilisant des mots de la langue commune. La reformulation représente le processus de réécriture qui a le rôle d’expliquer ou simplifier une phrase ou syntagme. Nous présentons la méthodologie de construction d’un jeu de données original (termes et reformulations) permettant la détection et génération des nouvelles reformulations médicales. Pour compléter ce corpus, nous menons des expériences de génération automatique de reformulations médicales sous-phrastiques avec l’outil APT (Nighojkar & Licato, 2021), qui s’appuie sur des techniques d’apprentissage profond. Nous adaptons le modèle de langue de type Transformer T5 (Raffel et al., 2020) avec des termes médicaux et leur reformulations annotés manuellement en français et en roumain, langue romane peu dotée en ressources pour le TAL. Nous présentons une analyse détaillée des résultats de la génération automatique des paraphrases.

Scientific medical terms are difficult to understand for laypeople due to their technical formulas and etymology. Understanding medical concepts is important for laypeople as personal and public health is a lifelong concern. In this study, we present our methodology for building a French lexical resource annotated with paraphrases for the simplification of monolexical and multiword medical terms. In order to find medical paraphrases, we automatically searched for medical terms and specific lexical markers that help to paraphrase them. We annotated the medical terms, the paraphrase markers, and the paraphrase. We analysed the lexical relations and semantico-pragmatic functions that exists between the term and its paraphrase. We computed statistics for the medical paraphrase corpus, and we evaluated the readability of the medical paraphrases for a non-specialist coder. Our results show that medical paraphrases from popularization texts are easier to understand (62.66%) than paraphrases extracted from scientific texts (50%).