Haein Kong
About Me
Hello! 👋 I’m Haein, a PhD candidate in Information Science at Rutgers University (Advisor: Prof. Vivek K. Singh).
My research examines persuasion and manipulation in human and AI-generated language, with a focus on their implications for AI safety and LLM evaluation.
I’m on the 2026–2027 job market, seeking industry Research Scientist positions in AI safety, LLM evaluation, and related areas.
Feel free to reach out if you’d like to connect or collaborate!
Research Interests
- AI Safety & LLM Evaluation
- Responsible AI, Fairness & Bias
- Persuasion, Manipulation, & Psycholinguistics
News
- [Sep, 2026] 🎉 Awarded the University and Louis Bevier Fellowship for the 2026-2027 academic year!
- [Aug, 2026] 🏆 Our team placed 3rd on the Black-Box Validation leaderboard in the Aletheia’s Quest Lie Detection Competition, earning an invitation to the event in Boston.
- [Apr, 2026] ✨ My summer internship project at the Digital Safety Research Institute (DSRI) was accepted to the HEAL Workshop at CHI 2026.
- [Oct. 2025] ✨ My first-author paper was accepted to IJCNLP-AACL Findings 2025.
More news
- [Jun. 2025] My co-first-authored paper has been published in New Media & Society.
- [May. 2025] I will join Digital Safety Research Institute as a research intern this summer ✨
- [Feb. 2025] I presented at WebSci’25 PhD symposium at Rutgers University, New Brunswick.
- [Nov. 2024] One paper has been accepted to SoLaR, NeurIPS 2024
- [Jul. 2024] Our paper has been accepted to WASSA workshop, ACL 2024
- [Jun. 2024] I will attend HCIC 2024 Annual Meeting
- [Jul. 2023] One paper got accepted to the 2023 UbiComp Mental Health workshop
- [Jun. 2023] I attended the 7th Summer School on Computational Interaction at the University of Michigan
Publications
-
IJCNLP/AACL Findings, 2025
-
New Media & Society, 2025
-
Socially Responsible Language Modelling Research (SoLaR) Workshop at NeurIPS, 2024
Powered by Jekyll and Minimal Light theme.