Dongyub (Jude) Lee
My research has spanned NLP, including dialogue systems, question answering, and LLM reliability, and has more recently expanded into multimodal AI. My current work and research interests focus on Healthcare AI and understanding how safety is represented in LLMs. I am particularly interested in research that advances our understanding of AI while also contributing to reliable, practical systems for real-world applications.
Since May 2024, I have been working as an AI Research Scientist at Zoom. Previously, I worked at Naver and Kakao, two of South Korea’s leading technology companies whose services are part of everyday life for nearly everyone in the country. These experiences have shaped my interest in both advancing AI research and building practical systems that can make a meaningful impact at scale.
Academic Activities
- Area Chair and Reviewer for ARR 2026.
- Reviewer of NAACL 2023, ACL 2023, and ARR 2023.
- Reviewer of ACL 2022 and NAACL 2022.
- Reviewer of ACL 2021 and EMNLP 2021.
News
- May 2024I have joined Zoom as an AI Research Scientist!
- Mar 2024Our paper "Tree-of-Question: Structured Retrieval Framework for Korean Question Answering Systems" has been accepted to NAACL 2024, Industry Track.
- Jan 2024Our paper "Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning" has been accepted to EACL 2024.
- Oct 2022Our paper on Dialogue Systems grounding Persona and Knowledge accepted to EACL 2022, Findings.
- Dec 2021Started working for Naver Search.
- Dec 2021Our paper on Dialogue State Tracking accepted to AAAI 2022, DSTC10.
- Oct 2021In the Dialogue State Tracking Challenge (DSTC 10) Track2, we achieved 3rd place in Task1 and 5th place in Task2 DSTC10.
- Sep 2021Our paper on dialogue summarization accepted to NewSum, EMNLP 2021.
- Jun 2021Our paper on disfluency detection accepted to INTERSPEECH 2021.
- May 2021Our paper on aspect-based sentiment analysis (DCRAN) accepted to ACL 2021.
- Dec 2020Our paper on multi-turn dialog system (UMS) got accepted to AAAI 2021.
- Oct 2020Our paper on summarization (RDASS) accepted to COLING 2020.
International Publications
2026
Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations
RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine Translation
2024
Tree-of-Question: Structured Retrieval Framework for Korean Question Answering Systems
Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning
2022
You Truly Understand What I Need : Intellectual and Friendly Dialog Agents grounding Persona and Knowledge
Towards Filling the Gap between Written and Spoken Dialogues for Multi-Domain Dialogue State Tracking
2021
Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization
Auxiliary Sequence Labeling Tasks for Disfluency Detection
Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis
Do Response Selection Models Really Know What’s Next? Utterance Manipulation Strategies for Multi-turn Response Selection
2020
Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization
An Effective Domain Adaptive Post-Training Method for BERT in Response Selection
Development of Fashion Product Retrieval and Recommendations Model Based on Deep Learning
2019
Integrating breakdown detection into dialogue systems to improve knowledge management: encoding temporal utterances with memory attention
EmotionX-KU: BERT-Max based Contextual Emotion Classifier
Enhanced Sequential Representation Augmented with Utterance-level Attention for Response Selection
2018
Character-Level Feature Extraction with Densely Connected Networks
Appointments & Awards
| Year | Award |
|---|---|
| 2021 | 3rd place in Task1 and 5th place in Task2, Dialogue State Tracking Challenge (DSTC 10) Track2, AAAI 2022 |
| 2019 | 2nd place in the EmotionX (shared task of SocialNLP), IJCAI 2019 |
| 2019 | Fourth place in the DSTC-7 tack-1 task, AAAI 2019 |
| 2018 | Bronze Prize in the Korean Language Information Processing Competition (Dependency Parser), HCLT 2018 |
| 2018 | Kakao Research Scholarship |
| 2017 | Gold Prize in Korean Language Information Processing Competition (Named Entity Recoginition), HCLT 2017 |
| 2016 | Software Maestro 6th (Completion of Phase 1, Advance to Phase 2) |