International Research Journal of Engineering and Technology (IRJET) Volume: 13 Issue: 02 | Feb 2026
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
Biomedical Abstract Simplification Using Large Language Models (LLMs) with Control Mechanism G. Thrishul1, B. Bharath Kumar2, K. Sai Karthik3, Ch. Sai Kiran4, D.Kavitha5 1234Department of Information Technology, TKR College of Engineering and Technology, Telangana, India
5Assistant Professor, Department of Information Technology, TKR College of Engineering and Technology,
Telangana, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Biomedical research articles often contain highly
considerable attention as it focuses on reducing linguistic complexity while preserving the original semantic meaning. In the biomedical domain, effective text simplification can improve knowledge dissemination, patient education, and cross-domain collaboration, making it a critical research area.
complex terminology and sentence structures, making them difficult to comprehend for non-expert readers, patients, and interdisciplinary researchers. This creates a significant accessibility gap between advanced medical research and its practical understanding. To address this challenge, this paper proposes an intelligent biomedical text simplification system based on a transformer-driven sequence-to-sequence architecture. The proposed system leverages a FLAN-T5 encoder–decoder model to convert complex biomedical abstracts into simplified, readable text while preserving core semantic meaning. The system incorporates preprocessing, tokenization, dense vector embeddings, contextual encoding, and beam search–based decoding to generate high-quality simplified outputs. Additionally, multiple simplification levels—mild, medium, and strong—are supported to cater to diverse user requirements. A Stream lit-based user interface enables real-time interaction and visualization of results. Experimental observations demonstrate that the proposed approach effectively enhances readability without significant loss of informational content, making biomedical literature more accessible and user-friendly.
1.2 Problem Statement Despite advancements in NLP, simplifying biomedical text remains a challenging task due to the presence of specialized vocabulary, long compound sentences, and context-sensitive meanings. Traditional rule-based and statistical approaches often fail to preserve critical medical information or produce oversimplified outputs that distort the original intent. Additionally, many existing systems lack flexibility in controlling the level of simplification, limiting their applicability to diverse user groups. There is a clear need for an intelligent and adaptive system capable of simplifying biomedical abstracts while maintaining contextual accuracy, semantic integrity, and readability. Such a system should also provide an interactive interface to allow users to experiment with different simplification levels in real time.
Key Words: Biomedical Text Simplification, Natural Language Processing, Transformer Models, FLAN-T5, Text Preprocessing, Beam Search Decoding, Stream lit Application
1.3 Objectives of the Proposed System The primary objective of the proposed system is to develop an intelligent and reliable biomedical text simplification framework that can automatically transform complex biomedical abstracts into simplified and easily understandable text. The system aims to reduce linguistic complexity while preserving the original semantic meaning and critical medical information, ensuring that the simplified output remains informative and contextually accurate. By focusing on biomedical abstracts, the proposed approach targets a highly specialized and information-dense form of text that presents unique challenges in natural language processing.
1. INTRODUCTION 1.1 Background and Motivation The rapid growth of biomedical research has resulted in an exponential increase in scientific publications, clinical reports, and healthcare documentation. While these resources are invaluable for medical professionals, they often contain complex terminology, dense sentence structures, and domain-specific expressions that are difficult to understand for non-expert readers, patients, and interdisciplinary researchers. This lack of accessibility creates a significant barrier between biomedical knowledge and its effective utilization.
Another key objective of this work is to leverage recent advancements in transformer-based architectures to improve contextual understanding and text generation quality. The proposed system utilizes a FLAN-T5 encoder– decoder model, which is specifically designed to handle sequence-to-sequence tasks efficiently. By exploiting its ability to capture long-range dependencies and contextual
Natural Language Processing (NLP) techniques have emerged as a powerful solution to bridge this gap by enabling automated understanding and transformation of textual data. Among these, text simplification has gained
© 2026, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 28