Research Interests

• Large Language Model
• Retrieval-augmented LMs
• Multi-step Reasoning

Education

• Ph.D. in Computer Science (Feb 2022), Yonsei University, Seoul, Korea
• B.S. in Electrical and Electronic Engineering (Feb 2016), Yonsei University, Seoul, Korea

Publications

• PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering
  Wookje Han, Jinsol Park, Kyungjae Lee*
  EMNLP 2023 (*corresponding authors).


• On Sample-Efficient Code Generation
  Hojae Han, Yu Jin Kim, Byoungjip Kim, Youngwon Lee, Kyungjae Lee, Kyungmin Lee, Moontae Lee, Kyunghoon Bae, Seung-won Hwang.
  EMNLP 2023.


• On Monotonic Aggregation for Open-domain QA
  Sang-eun Han, Yeonseok Jeong, Seung-won Hwang, Kyungjae Lee
  INTERSPEECH 2023. [LINK]


• QASA: Answering Advanced Questions on Scientific Articles
  Yoonjoo Lee*, Kyungjae Lee*, Sunghyun Park, Dasol Hwang, Jaehyeon Kim, Hong-in Lee, Moontae Lee.
  ICML 2023 (*co-first authors). [LINK] [Data]


• When to Read Documents or QA History: On Unified and Selective Open-domain QA
  Kyungjae Lee*, Sang-eun Han*, Seung-won Hwang, Moontae Lee.
  Findings of ACL 2023 (*co-first authors). [LINK]


• On Complementarity Objectives for Hybrid Retrieval
  Dohyeon Lee, Seung-won Hwang, Kyungjae Lee, Seungtaek Choi, Sunghyun Park.
  ACL 2023. [LINK]


• Exploring the Benefits of Training Expert Language Models over Instruction Tuning
  Joel Jang, Seungone Kim, Seonghyeon Ye, Doyoung Kim, Lajanugen Logeswaran, Moontae Lee, Kyungjae Lee, Minjoon Seo.
  ICML 2023. [LINK] [Code]


• Plug-and-Play Adaptation for Continuously-updated QA
  Kyungjae Lee, Wookje Han, Seung-won Hwang, Hwaran Lee, Joonsuk Park, Sang-Woo Lee.
  ACL 2022 (Findings). [LINK]


• Robustifying Multi-hop QA through Pseudo-Evidentiality Training
  Kyungjae Lee, Seung-won Hwang, Sang-eun Han, Dohyeon Lee.
  ACL 2021. [LINK]


• Query Generation for Multimodal Documents.
  Kyungho Kim, Kyungjae Lee, Seung-won Hwang, Young-In Song, Seungwook Lee.
  EACL 2021. [LINK]


• Instructional Video Summarization using Attentive Knowledge Grounding.
  Kyungho Kim*, Kyungjae Lee* and Seung-won Hwang.
  ECML-PKDD 2020 (*co-first authors) [PDF]


• Segment-then-Rank: Non-factoid Question Answering on Instructional Videos.
  Kyungjae Lee, Nan Duan, Lei Ji, Jason Li, and Seung-won Hwang.
  AAAI 2020 [PDF]


• Learning with Limited Data for Multilingual Reading Comprehension.
  Kyungjae Lee*, Syunhyun Park*, Hojae Han, Jinyoung Yeo, Seung-won Hwang, and Juho Lee.
  EMNLP 2019 (*co-first authors, oral presentation) [PDF]


• Categorical Metadata Representation for Customized Text Classification.
  Jihyeok Kim*, Reinald Kim Amplayo*, Kyungjae Lee, Sua Sung, Minji Seo, and Seung-won Hwang.
  TACL 2019 (*co-first authors). [PDF] [Code/Data]


• Semi-supervised Training Data Generation for Multilingual Question Answering.
  Kyungjae Lee, Kyungho, Yoon, Syunhyun Park, and Seung-won Hwang.
  LREC 2018. [PDF] [Data]


• Translations as Additional Contexts for Sentence Classification.
  Reinald Kim Amplayo, Kyungjae Lee, Jinyoung Yeo, and Seung-won Hwang.
  IJCAI 2018. [PDF] [Code/Data]


• Gradable Adjective Embedding for Commonsense Knowledge.
  Kyungjae Lee, Hyunsouk Cho, and Seung-won Hwang.
  PAKDD 2017. [PDF]

Services & Talks

• Talk: Future Research Information Forum (미래연구정보포럼) 2023.12 [LINK]
• Talk: AI Summer School 2021, Seoul National University [LINK]
• Reviewer for conference/journal: ACL (2020~), EMNLP (2021~), NAACL (2021), VLDB (2019, 2020)

Work & Teaching Experience

• Lecturer, Yonsei University, Artificial Intelligence (CS4108) (Spring 2020)
• Microsoft Research Asia, Internship (Sep 2018 ~ Mar 2019)

Awards & Scholarships

• NAVER Ph.D. Fellowship Award 2019
• Google Travel Grant for EMNLP 2019
• Global Ph.D. Fellowship (funding for 5 years), from National Research Foundation of Korea
• BIG 2017 CUP Data competition 3rd winner, sponsored by Microsoft
• Yonsei Undergraduate Scholarship 2012-2015 (fully funded)
• Undergraduate, 2012-2013 semesters, GPA honors