Interactive active learning for literature screening: finetuning GPT with DeepSeek reasoning for cross-domain generalization
We propose an active learning framework that leverages disagreement between large language models (GPT and DeepSeek) to selectively fine-tune GPT models with reasoning-augmented supervision, significantly improving accuracy and recall in automated biomedical literature screening.
Mar 9, 2026
Testing and evaluation of generative large language models in electronic health record applications: a systematic review
Our systematic review shows that current evaluations of LLMs in real clinical settings are surprisingly narrow and mostly focused on radiology and decision support, while key areas like patient communication remain largely under-explored.
Jan 13, 2026
AI-assisted literature screening: A hybrid approach using large language models and retrieval-augmented generation
This study aims to improve literature screening efficiency and accuracy by developing an LLM-based approach that incorporates rule-based preprocessing, prompt engineering (including RAG), and ensemble techniques.
Nov 30, 2025
Performance and improvement strategies for adapting generative large language models for electronic health record applications: A systematic review
We conduct a comprehensive review of recent studies that leverage generative LLMs for EHR analysis and applications, focusing on their performance and strategies for improvement.
Aug 25, 2025
Precision Grounding: Augmenting Large Language Models with Evidence-Based Databases for Trustworthy Genetic Variant Summarization
LLMs are prone to generating inaccurate or misleading interpretation of genetic variants. To solve this, we propose a “precision grounding” approach that enhances LLM with publicly available evidence-based databases and resources identified by domain experts.
Jun 9, 2025