Selected work

Representative Papers

Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why

Jun 17, 2026

This study addresses the challenge of extracting clinically relevant information from heterogeneous electronic health records, where patient data are scattered across numerous unstructured documents and structured entries lacking document-level metadata. Conventional retrieval-augmented generation (RAG) approaches struggle to support temporal reasoning and cross-document dependency modeling under such conditions. To overcome these limitations, this work proposes ACIE, a locally deployed agent-based RAG system tailored for real-world clinical information extraction. ACIE explicitly handles missing metadata, enables cross-document reasoning, and provides traceable citations to ensure interpretability and verifiability. Evaluated on 7,326 clinical judgments, the system achieved an overall physician acceptance rate of 96.5%, with per-category acceptance rates ranging from 80% to 99%.

0 citationsRead paper

AIANO: Enhancing Information Retrieval with AI-Augmented Annotation

Feb 04, 2026

This work addresses the inefficiency of traditional information retrieval dataset annotation, which relies on generic tools and struggles to meet the growing demand for high-quality question-answering data driven by large language models and retrieval-augmented generation (RAG). To overcome this limitation, the authors propose AIANO, a human-AI collaborative annotation tool that integrates large language model suggestions, an interactive interface, and a RAG-oriented workflow. While preserving full annotator control, AIANO significantly enhances both annotation efficiency and quality. User studies demonstrate that AIANO nearly doubles annotation speed compared to baseline tools, offers superior usability, and effectively improves downstream retrieval accuracy.

0 citationsRead paper

Evaluating Compliance with Visualization Guidelines in Diagrams for Scientific Publications Using Large Vision Language Models

Jun 24, 2025

Scientific publications frequently contain figures that violate visualization best practices, risking misrepresentation or misinterpretation of data. To address this, we propose the first automated chart compliance assessment framework based on large vision-language models (VLMs), systematically evaluating five open-source VLMs—including Qwen2.5VL—on critical issues such as chart-type classification, 3D distortion detection, legend omission, and missing axis labels. We design visualization-rule-aware prompting strategies and employ multi-dimensional quantitative evaluation using F1-score and RMSE. Our framework achieves strong performance: chart-type identification (F1 = 82.49%), 3D effect detection (F1 = 98.55%), and legend presence detection (F1 = 96.64%). This work constitutes the first systematic validation of VLMs for scientific figure quality auditing, establishing a reproducible methodological foundation for automated scientific image governance.

0 citationsRead paper

A Multimodal Pipeline for Clinical Data Extraction: Applying Vision-Language Models to Scans of Transfusion Reaction Reports

Apr 28, 2025

Paperwork-based medical forms and manual transcription lead to low efficiency and high error rates, undermining regulatory reporting accuracy. This study introduces the first open-source multimodal pipeline for end-to-end automated extraction and classification of checkbox data from scanned transfusion reaction reports. The pipeline integrates checkbox detection (YOLOv8), multilingual OCR (PaddleOCR), and a multilingual vision-language model (mPLUG-Owl2). Its key innovation lies in the first integration of a multilingual VLM into clinical form parsing—enabling zero-shot transfer to other checkbox-dense documents. Evaluated on gold-standard data spanning 2017–2024, the system achieves high precision and recall, substantially reducing administrative burden while ensuring regulatory compliance. The fully open-sourced implementation supports local deployment and multilingual adaptation.

0 citationsRead paper

Recent publications

Latest Papers

Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why

Jun 17, 2026

This study addresses the challenge of extracting clinically relevant information from heterogeneous electronic health records, where patient data are scattered across numerous unstructured documents and structured entries lacking document-level metadata. Conventional retrieval-augmented generation (RAG) approaches struggle to support temporal reasoning and cross-document dependency modeling under such conditions. To overcome these limitations, this work proposes ACIE, a locally deployed agent-based RAG system tailored for real-world clinical information extraction. ACIE explicitly handles missing metadata, enables cross-document reasoning, and provides traceable citations to ensure interpretability and verifiability. Evaluated on 7,326 clinical judgments, the system achieved an overall physician acceptance rate of 96.5%, with per-category acceptance rates ranging from 80% to 99%.

0 citationsRead paper

AIANO: Enhancing Information Retrieval with AI-Augmented Annotation

Feb 04, 2026

This work addresses the inefficiency of traditional information retrieval dataset annotation, which relies on generic tools and struggles to meet the growing demand for high-quality question-answering data driven by large language models and retrieval-augmented generation (RAG). To overcome this limitation, the authors propose AIANO, a human-AI collaborative annotation tool that integrates large language model suggestions, an interactive interface, and a RAG-oriented workflow. While preserving full annotator control, AIANO significantly enhances both annotation efficiency and quality. User studies demonstrate that AIANO nearly doubles annotation speed compared to baseline tools, offers superior usability, and effectively improves downstream retrieval accuracy.

0 citationsRead paper

Evaluating Compliance with Visualization Guidelines in Diagrams for Scientific Publications Using Large Vision Language Models

Jun 24, 2025

Scientific publications frequently contain figures that violate visualization best practices, risking misrepresentation or misinterpretation of data. To address this, we propose the first automated chart compliance assessment framework based on large vision-language models (VLMs), systematically evaluating five open-source VLMs—including Qwen2.5VL—on critical issues such as chart-type classification, 3D distortion detection, legend omission, and missing axis labels. We design visualization-rule-aware prompting strategies and employ multi-dimensional quantitative evaluation using F1-score and RMSE. Our framework achieves strong performance: chart-type identification (F1 = 82.49%), 3D effect detection (F1 = 98.55%), and legend presence detection (F1 = 96.64%). This work constitutes the first systematic validation of VLMs for scientific figure quality auditing, establishing a reproducible methodological foundation for automated scientific image governance.

0 citationsRead paper

A Multimodal Pipeline for Clinical Data Extraction: Applying Vision-Language Models to Scans of Transfusion Reaction Reports

Apr 28, 2025

Paperwork-based medical forms and manual transcription lead to low efficiency and high error rates, undermining regulatory reporting accuracy. This study introduces the first open-source multimodal pipeline for end-to-end automated extraction and classification of checkbox data from scanned transfusion reaction reports. The pipeline integrates checkbox detection (YOLOv8), multilingual OCR (PaddleOCR), and a multilingual vision-language model (mPLUG-Owl2). Its key innovation lies in the first integration of a multilingual VLM into clinical form parsing—enabling zero-shot transfer to other checkbox-dense documents. Evaluated on gold-standard data spanning 2017–2024, the system achieves high precision and recall, substantially reducing administrative burden while ensuring regulatory compliance. The fully open-sourced implementation supports local deployment and multilingual adaptation.

0 citationsRead paper