Jiseon Kim
Scholar

Jiseon Kim

Google Scholar ID: RNmRwOoAAAAJ
KAIST
Natural Language ProcessingComputational Social Science
Citations & Impact
All-time
Citations
194
 
H-index
6
 
i10-index
6
 
Publications
10
 
Co-authors
19
list available
Resume (English only)
Academic Achievements
  • 1. Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models, EMNLP 2024
  • 2. HyperCLOVA X Technical Report, Technical Report 2024
  • 3. KoBBQ: Korean Bias Benchmark for Question Answering, TACL 2024, Presented at ACL 2024
  • 4. Learning Bill Similarity with Annotated and Augmented Corpora of Bills, EMNLP 2021
  • 5. Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning, EMNLP 2021
  • 6. Dimensional emotion detection from categorical emotion, EMNLP 2021
  • 7. Denoising recurrent neural networks for classifying crash-related events, IEEE transactions on intelligent transportation systems 2019
  • 8. Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment, BiAlign @ ICLR 2025
  • 9. Understanding Lobbying Strategies in Legislative Process: Bill Position Dataset and Lobbying Analysis, WiML@NeurIPS 2024
  • 10. Measuring Interest Group Positions on Legislation: An AI-Driven Analysis of Lobbying Reports, arXiv 2025
  • 11. Uncovering Factor Level Preferences to Improve Human-Model Alignment, arXiv 2024
Research Experience
  • 1. Visiting Researcher at MIT: Summer 2019, 2022, 2024
  • 2. Research Intern at NAVER AI Lab: March 2023 - June 2023
  • 3. Researcher at KAIST: March 2019 - February 2020
Education
  • 1. Korea Advanced Institute of Science and Technology (KAIST), School of Computing, Ph.D. Candidate, 2020 - Present
  • 2. Korea Advanced Institute of Science and Technology (KAIST), School of Computing, M.S., 2017 - 2019
  • 3. Sookmyung Women's University, B.S. in Computer Science, 2013 - 2017
Background
  • Ph.D. candidate at KAIST, working in the User & Information Lab (U&I Lab), advised by Alice Oh. Research interests include natural language processing (NLP) and computational social science (CSS), with a focus on AI alignment with human and societal values and AI for social good.