← Back to all news
arXiv Computation and Language

Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation

The paper explores how Large Language Models (LLMs) such as GPT-4o-mini, Gemini-1.5-pro, and LLaMA can be used to automatically simplify complex medical texts into plain language, a process known as Plain Language Adaptation (PLA). It evaluates different prompting strategies, fine‑tunes models with QLoRA, and incorporates Mixture‑of‑Agents (MoA) techniques to improve adaptability and robustness. The results show that LLM‑driven PLA effectively makes healthcare information more comprehensible while preserving essential content.

Related stories

arXiv Computation and Language
Sep 7

MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering

MedProb is a lightweight probing framework that predicts multiple-choice medical visual question answering (Med‑VQA) answers directly from frozen vision‑language model (VLM) representations, avoiding free‑text generation. On datasets such as PATH‑VQA, SLAKE, and VQA‑RAD, MedProb extracts more answer‑relevant signal than prompting and outperforms both medical VLMs and agentic systems. The approach also narrows the performance gap between small and large models, shows that medical adaptation does not consistently improve linear decodability, and reveals positional biases in both prompting and generation.

By Erfan Nourbakhsh, Ke Yang, Anthony Rios
llmsagentsnlpfine-tuningmultimodalsafety
More like this →
arXiv Computation and Language
Oct 22

Edit Policy-Aligned Text Simplification

The paper introduces a method for text simplification that uses a Large Language Model-as-a-Judge (LLM‑Judge) to automatically generate policy‑aligned training data, eliminating the need for costly human annotation or parallel corpora. This approach allows simplification models to adapt to various policies—such as lexical‑focused simplification or overall rewriting that trades detail for simplicity—at both sentence and document levels. Experiments show that small‑scale open‑source LLMs can match or surpass GPT‑5, with consistent improvements across model families and sizes.

By Xuanxin Wu, Yuki Arase, Masaaki Nagata
llms
More like this →
arXiv Computation and Language
Oct 22

PRiME: Pragmatic Reasoning In MEntal health

The paper PRiME investigates how large language models (LLMs) can perform pragmatic reasoning in the mental health domain. It introduces three datasets and tasks, evaluates 12 LLMs—including the specialized MentaLLaMA model—and finds that performance is comparable to human evaluation, with Mistral‑7B achieving the best results. The study also examines error asymmetry and uses first‑order attention rollout to analyze MentaLLaMA‑7B’s architectural behavior, urging careful analysis for high‑stakes applications.

By Sneha Oram, Tejomay Kishor Padole, Pushpak Bhattacharyya, Suyash P. Awate
llms
More like this →
arXiv AI
Sep 15

Medical Knowledge Simplification for Patients in the Era of LLMs: A Case Study on Diabetes

The paper presents MediClear, an LLM-based system that simplifies diabetes-related medical information for patients. By indexing public articles from Diabetes Australia, WHO, ADA, NIDDK, and AIHW in a Retrieval-Augmented Generation knowledge base, MediClear retrieves clinically grounded content and rewrites it into patient-friendly language. Evaluation shows the system consistently lowers reading levels to the recommended patient literacy range and receives high user satisfaction in a human study.

By Pallika Kafle, Yipeng Zhou, Guanfeng Liu, Quan Z. Sheng, Cheng-Hsin Hsu
llmsrag
More like this →