About Me
I am a NLP researcher and a student at the University of Pennsylvania. My research interests lie at the intersection of language models, cognitive understanding of it, and its alignment.
I'm currently working on alignment and representation engineering at IBM Research. Previously, I was a research intern at Naver Cloud for HyperCLOVA X models, and researched dark matter at the Institute for Basic Science in South Korea. I also worked as a research engineer at a startup, where I began my NLP career exploring its applications in education.
Research Interests
- Large Language Models
- Natural Language Processing
- Handcrafted Linguistic Features
Open Source Softwares
LFTK
A lightweight version of LingFeat that extracts stylistic features from arbitrary natural language. Used and trusted by research institutions around the world.
LingFeat
A comprehensive Python package for extracting 255 handcrafted linguistic features from English.
Selected Publications
ACL 2024 - Lee, Bruce W., and JaeHyuk Lim. "Language Models Don't Learn the Physical Manifestation of Language."
NAACL 2024 - Lee, Bruce W., Hyunsoo Cho, and Kang Min Yoo. "Instruction Tuning with Human Curriculum."
EACL 2023 - Lee, Bruce W., and Jason Lee. "Prompt-based Learning for Text Readability Assessment."
BEA@ACL 2023 - Lee, Bruce W., and Jason Hyung-Jong Lee. "LFTK: Handcrafted features in computational linguistics."
EMNLP 2021 - Lee, Bruce W., Yoo Sung Jang, and Jason Lee. "Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features."
Experience
- Research Intern, IBM Research
- Research Intern, NAVER Cloud
- Research Engineer, LXPER
- Research Scholar, Center for Axion and Precision Physics Research, Institute for Basic Science
Contact
Email: {id}@seas.{school}.edu. id is brucelws and school is upenn