Research

MedEvi-NS at ArchEHR-QA 2026: Using clinical reasoning principles to improve zero-shot capabilities of Large Language Models in Evidence Alignment

Mengxuan Sun, Nicolay Rusnachenko

LREC-COLING 2026 / ArchEHR-QA 2026 Task 4 Competition
Contest

Using Decoder-Based Distillation for Enhancing Multilingual Clinical Case Report Summarization

Nicolay Rusnachenko, Xiaoxiao Liu, Jian Chang, Jian Jun Zhang

CLEF-2025 / BioASQ-2025
9–12 September 2025, Madrid, Spain
Oral Presentation

Proceeding of the MediExtract framework, reforged for decoder-based models (LLMs) with role-based prompt formation. The reforged version has scalable potential for other modalities.

Using Large Language Models for Evaluation of Radiological Textual Reports

Nicolay Rusnachenko, James Franklin, Theophilus Akudjedu, Neel Doshi, Michael Board, Jian Chang, Jian Jun Zhang

CASA-2025 and AniNex Workshop
2–4 June 2025, Strasbourg, France
Poster Presentation

Enhancing Medical Dialogue Summarization: A MediExtract Distillation Framework

Xiaoxiao Liu, Mengqing Huang, Nicolay Rusnachenko, Julia Ive, Jian Chang, Jian Jun Zhang

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
3–6 December 2024, Lisbon, Portugal
Oral Presentation

MediExtract Distillation Framework (MEDF) is a hybrid teacher-student distillation process that leverages the power of LLMs in information capturing to enhance the performance of a smaller student model.