Minbyul Jeong

Hi! I am Minbyul Jeong, a Ph.D. at Korea University under the supervision of Professor Jaewoo Kang.

I am passionate about solving real-world medical problems, such as answering patients' questions, developing medical conversational agents, and summarizing Electronic Health Records. My primary goal is to create a medical agent that can assist physicians and doctors in their practice.

Email / CV / Google Scholar / LinkedIn / X / Github / Youtube

Question Answering: I study how to develop methods for specific domain such as biomedical and clinical. I study for the method of real-time question answering (CovidASK), solving specific challenging problem (BioBERT-QA, Transferability QA, and Data Centric QA). These days, I study to address patients' questions which could truly help in real world situations: Self-BioRAG and OLAPH.
Named Entity Recognition: My primary goal for NER task is to extract necessary biomedical knowledge from the ever-growing biomedical literature for domain researchers. Thus, I made automatic system to extract biomedical knowledge from literature (BERN, BERN2), consistent prediction in document context (ConNER).
Graph-based Learning: My earlier works include systems for graph neural networks which are widely used in representation learning on graphs including GTN, FastGTN, HATS, and PubMed KG.

09.2024. 1 unveiling chronological knowledge in 5 domains released: ChroKnowledge.
09.2024. 1 compression paper accepted @ EMNLP'24: CompAct.
08-.2024. I will be joining a LLM team at Upstage.
06.2024. I've done my Ph.D student process at Korea University.
05.2024. 1 Medical Long-form Question Answering paper with improving factuality released: OLAPH.
01.2024. 1 medical domain RAG paper accepted @ ISMB'24: Self-BioRAG.
05.2023. BioNER paper accepted @ Bioinformatics'23: ConNER.
05.2022. NER+NEN framework paper accepted @ Bioinformatics Appnote'22: BERN2.
03.2022. learning meta-path GNN paper accepted @ Neural Networks'22: FastGTN.
07.2019. learning graph representation GNN paper accepted @ NeurIPS'19: GTN.

Selected Publications

Question Answering Benchmark Datasets Factuality & Hallucination
OLAPH: Improving Factuality in Biomedical Long-form Question Answering
Minbyul Jeong, Hyeon Hwang, Chanwoong Yoon, Taewhoo Lee, Jaewoo Kang,
Preprint.

arXiv / code / Youtube / Google Scholar

We present MedLFQA, a benchmark dataset reconstructed using long-form question-answering. We also introduce OLAPH, a framework leverages automatic evaluation to generate synthetic preference sets that can help align the model with preferred responses.

Question Answering Retrieval Augmented generation Instruction-tuned LLM
Self-BioRAG: Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models
Minbyul Jeong, Jiwoong Sohn, Mujeen Sung, Jaewoo Kang,
ISMB 2024.

arXiv / code / Google Scholar

We present Self-BioRAG, a domain-specific LLM version of Self-RAG framework.

Named Entity Recognition Consistency
ConNER: Consistency enhancement of model prediction on document-level named entity recognition
Minbyul Jeong, Jaewoo Kang,
Bioinformatics 2023.

paper / code / Google Scholar

We present ConNER, a biomedical NER training framework to enhance label consistency in document-level context.

Named Entity Recognition Named Entity Normalization
BERN2: an advanced neural biomedical named entity recognition and normalization tool
Mujeen Sung*, Minbyul Jeong*, Yonghwa Choi, Donghyeon Kim, Jinhyuk Lee, Jaewoo Kang,
Bioinformatics Appnote 2022.

demo / paper / code / Google Scholar

We present BERN2, a biomedical NER and NEN framework to automatically extract biomedical entities in biomedical literature. It only spent 0.3sec per document.

Graph-based Learning
Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs
Seongjun Yun, Minbyul Jeong, Sungdong Yoo, Seunghun Lee, Sean S. Yi, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim,
Neural Networks 2022.

paper / code / Google Scholar

We present FastGTN, a network improve scalability of graph transformations from previous version of Graph Transformer Networks (GTN).

Graph-based Learning
Graph Transformer Networks
Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim,
NeurIPS 2019.

paper / code / Google Scholar

We present GTN, a network for graph transformations to enhance node representations.

Other activities

Reviewing activities

Serving as a reviewer for following conferences and journals:
Experimental & Theoretical Artificial Intelligence'24
Neural Networks'23
Knowledge-Based Systems'23
Applied Intelligence'22,23
Data Technologies and Applications'22

Awards & Honors

[BioASQ 9B, 03-05.2021] 1st Place: A challenge on large-scale biomedical semantic indexing and question answering
[BioASQ 8B, 03-05.2020] 1st Place: A challenge on large-scale biomedical semantic indexing and question answering
[BioASQ 7B, 03-05.2019] 1st Place: A challenge on large-scale biomedical semantic indexing and question answering

Template based on Jon Barron's website.

Research Interests

News

Selected Publications

Other activities