This study introduces a novel methodology leveraging publicly accessible online health forums to systematically build an unbiased, privacy-conscious QA dataset, and it employs Topic-guided Semantic Modeling (TGSM) for automated topic identification, enabling efficient and targeted annotation of relevant patient-generated content.
Abstract
The application of question-answering (QA) systems in the medical domain has rapidly advanced, significantly improving patients’ access to reliable health-related information. However, current approaches face notable challenges, including the difficulty in obtaining large-scale and unbiased medical datasets, significant privacy concerns, and inefficiencies due to manual dataset annotation. To address these issues, This study introduce a novel methodology leveraging publicly accessible online health forums to systematically build an unbiased, privacy-conscious QA dataset, and it employs Topic-guided Semantic Modeling (TGSM) for automated topic identification, enabling efficient and targeted annotation of relevant patient-generated content. Subsequently, this study propose a two-stage QA pipeline based on a Retriever–Reader architecture, which is further enhanced through fine-tuning state-of-the-art transformer-based models on the constructed domain-specific QA dataset. Experimental results demonstrate that our fine-tuned BioBERT significantly outperforms existing benchmarks, offering accurate patient-derived insights and providing a replicable framework for building efficient medical QA systems.
A comprehensive survey of various benchmark datasets used in medical LLM tasks, focusing on various aspects of medical knowledge such as electronic health records, doctor–patient dialogues, medical question answering, and medical image captioning, is presented.
L. K. Yan, Qian Niu, Ming Li et al.· Medicine Advances· 34 citations· ⚡1
Extensive experiments across multiple medical question-answering benchmarks demonstrate that models fine-tuned with SAGE-synthesized data consistently outperform those trained using self-derived or conventional document-based paradigms, highlighting tangible improvements in data efficiency and resource utilization for...
Chuan Li, Chengyu Wang, Cen Chen et al.· Proceedings of the 2026 Conf...· 0 citations
A novel framework that leverages the language understanding and code generation ability of Large Language Models (LLMs) to build an information retrieval system with Visualization-oriented Natural-language-based Inter-faces (V-NLI).
Xin Gao, Zheng-Ye Zhu, Xin-Yu Ma et al.· Tsinghua Science and Technol...· 0 citations
A scalable framework that automatically generates question--answer pairs from longitudinal EHR notes that supports evaluations that static benchmarks cannot, including the generation of multiple answers that reflect variation in clinician reasoning for robust performance assessment and continuously refreshing benchmark...
J. Cahoon, C. Stanwyck, Sulaiman Somani et al.· arXiv.org· 1 citation
This review explores the transformative impact of Large Language Models on medical question-answering robots and addresses critical challenges faced by LLM-driven systems, such as limited interpretability, restricted applicability across medical domains, and serious concerns about patient privacy.
Zhao-Xu Wang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.