Tag
MedGuards proposes a multi-agent framework for detecting and correcting errors in medical text using specialized agents and confidence-guided arbitration, improving reliability without additional training. Experiments on multilingual clinical notes show significant improvements.
This paper introduces a benchmark of 1,200 clinical documents with 9,184 uncertainty annotations to evaluate whether LLMs preserve diagnostic uncertainty in clinical text, finding that LLMs often fail to preserve original uncertainty cues and struggle with nuanced distinctions.
This paper introduces ChristBERT, a family of domain-specific RoBERTa-based language models for German clinical NLP, and evaluates three domain adaptation strategies (continued pre-training, pre-training from scratch, and vocabulary adaptation) on medical named entity recognition and text classification tasks, achieving state-of-the-art results.
This paper presents a specialty-specific medical language model for extracting information from clinical narratives about immune-mediated and infectious diseases, using a BiLSTM-CNN-Char architecture trained on a curated corpus of 371 case reports, achieving an F1 score of 0.89.
Proposes an agentic framework using LangChain agents for population-scale mental health screening, focusing on depression detection from clinical transcripts. The framework incrementally locks validated stages and uses proxy-guided evaluation to ensure trustworthiness and adaptability.