Paper Review & Presentation
Sampling from Your Language Model One Byte at a Time.
Jonathan Hayase,
Lee DongWon,
Noah A. Smith,
Sewoong Oh.
Preprint 2025.
Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations.
Brian Siyuan Zheng,
Lee DongWon,
Orevaoghene Ahia,
Jonathan Hayase,
Yejin Choi,
Noah A. Smith.
NeurIPS 2025 (Spotlight 🌟).
SuperBPE: Space Travel for Language Models.
Lee DongWon*,
Jonathan Hayase*,
Sewoong Oh,
Noah A. Smith,
Yejin Choi.
COLM 2025.
Tulu 3: Pushing Frontiers in Open Language Model Post-Training.
Nathan Lambert,
Jacob Morrison,
Valentina Pyatkin,
Shengyi Huang,
Hamish Ivison,
Faeze Brahman,
Lester James V. Miranda,
Lee DongWon,
Nouha Dziri,
Shane Lyu,
Yuling Gu,
Saumya Malik,
Victoria Graf,
Jena D. Hwang,
Jiangjiang Yang,
Ronan Le Bras,
Oyvind Tafjord,
Chris Wilhelm,
Luca Soldaini,
Noah A. Smith,
Yizhong Wang,
Pradeep Dasigi,
Hannaneh Hajishirzi.
COLM 2025.
Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models.
Hila Gonen,
Terra Blevins,
Lee DongWon,
Luke Zettlemoyer,
Noah A. Smith.
NAACL 2025.
LlamaPIE: Proactive In-Ear Conversation Assistants.
Tuochao Chen,
Nicholas Batchelder,
Lee DongWon,
Noah Smith,
Shyamnath Gollakota.
ACL Findings 2025.
Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?.
Jonathan Hayase*,
Lee DongWon*,
Yejin Choi,
Sewoong Oh,
Noah A. Smith.
NeurIPS 2024.
Tuning Language Models by Proxy.
Lee DongWon,
Xiaochuang Han,
Yizhong Wang,
Yulia Tsvetkov,
Yejin Choi,
Noah A. Smith.
COLM 2024 (Spotlight 🌟, top 7%).
We're Afraid Language Models Aren't Modeling Ambiguity.
Lee DongWon,
Zhaofeng Wu,
Julian Michael,
Alane Suhr,
Peter West,
Alexander Koller,
Swabha Swayamdipta,
Noah A. Smith,
Yejin Choi.
EMNLP 2023.
That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context?.
Jaechan Lee,
Lee DongWon,
Orevaoghene Ahia,
Hila Gonen,
Noah A. Smith.
EMNLP Findings 2023.
Inverse Scaling: When Bigger Isn't Better.
Ian R. McKenzie,
18 others,
Lee DongWon,
Jiacheng Liu,
Tom Tseng,
Tomasz Korbak,
Najoung Kim,
Samuel R. Bowman,
Ethan Perez.
TMLR 2023 (Featured 🌟).
How Language Model Hallucinations Can Snowball.
Muru Zhang,
Ofir Press,
William Merrill,
Lee DongWon,
Noah A. Smith.
ICML 2024.
Self-Instruct: Aligning Language Models with Self-Generated Instructions.
Yizhong Wang,
Yeganeh Kordi,
Swaroop Mishra,
Lee DongWon,
Noah A. Smith,
Daniel Khashabi,
Hannaneh Hajishirzi.
ACL 2023.
Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts.
Skyler Hallinan,
Lee DongWon,
Yejin Choi,
Maarten Sap.
ACL 2023.
WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation.
Lee DongWon,
Swabha Swayamdipta,
Noah A. Smith,
Yejin Choi.
EMNLP Findings 2022.
Generated Knowledge Prompting for Commonsense Reasoning.
Jiacheng Liu,
Lee DongWon,
Ximing Lu,
Sean Welleck,
Peter West,
Ronan Le Bras,
Yejin Choi,
Hannaneh Hajishirzi.
ACL 2022.
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts.
Lee DongWon,
Maarten Sap,
Ximing Lu,
Swabha Swayamdipta,
Chandra Bhagavatula,
Noah A. Smith,
Yejin Choi.
ACL 2021.
Model Selection for Deep Audio Source Separation via Clustering Analysis.
Lee DongWon,
Prem Seetharaman,
Bryan Pardo.
DCASE 2020 (
Best Student Paper Award).
Incorporating Music Knowledge in Continual Dataset Augmentation for Music Generation.
Lee DongWon,
Alex Fang,
Gaëtan Hadjeres,
Prem Seetharaman,
Bryan Pardo.
ML4MD Workshop at ICML 2020.
Bach or Mock? A Grading Function for Chorales in the Style of J.S. Bach.
Alex Fang,
Lee DongWon,
Prem Seetharaman,
Bryan Pardo.
ML4MD Workshop at ICML 2020.
CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense.
Michael Chen,
Mike D’Arcy,
Lee DongWon,
Jared Fernandez,
Doug Downey.
RepEval Workshop at NAACL 2019.