Howard Yen

Howard Yen

顏和光

hyen [at] princeton [dot] edu
googlescholargithublinkedintwitteremail

Last updated: 2024/10/14

Hi I'm Howard!

I'm a Computer Science PhD student at Princeton University, advised by Professor Danqi Chen. Previously, I also obtained my BSE at Princeton in 2023. I'm part of the Princeton Natural Language Processing Group and Princeton Language and Intelligence.

My research focuses on benchmarking and enhancing language technologies with an emphasis on efficiency, reasoning, and attribution. Previously, I have developed long-context and reasoning-intensive benchmarks as well as methods to improve the performance of long-context models. You can find a copy of my CV here.

In my free time, I like to read, cook, and run. I used to serve as the Vice Chair of Princeton Association of Computing Machinery (ACM).

Publications

HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly
Howard Yen, Tianyu Gao, Minmin Hou, Ke Ding, Daniel Fleischer, Peter Izsak, Moshe Wasserblat, and Danqi Chen.
Preprint 2024
[Paper] [Code]
How to Train Long-Context Language Models (Effectively)
Tianyu Gao*, Alexander Wettig*, Howard Yen, and Danqi Chen.
Preprint 2024
[Paper] [Code]
BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
Hongjin Su*, Howard Yen*, Mengzhou Xia*, Weijia Shi, Niklas Muennighoff, Han-yu Wang, Haisu Liu, Quan Shi, Zachary S. Siegel, Michael Tang, Ruoxi Sun, Jinsung Yoon, Sercan O. Arik, Danqi Chen, and Tao Yu
Preprint 2024
[Paper] [Code]
Long-Context Language Modeling with Parallel Context Encoding
Howard Yen, Tianyu Gao, and Danqi Chen
ACL 2024
[Paper] [Code]
Improving Interpersonal Communication by Simulating Audiences with Language Models
Ryan Liu, Howard Yen, Raja Marjieh, Thomas L. Griffiths, and Ranjay Krishna
Preprint 2023
[Paper] [Code]
Enabling Large Language Models to Generate Text with Citations
Tianyu Gao, Howard Yen, Jiatong Yu, and Danqi Chen
EMNLP 2023
[Paper] [Code]
MoQA: Benchmarking Multi-Type Open-Domain Question Answering
Howard Yen, Tianyu Gao, Jinhyuk Lee, and Danqi Chen
DialDoc Workshop @ ACL 2023
[Paper] [Code]

* denotes equal contribution.

Contact

If you are interested in chatting about research, feel free to reach out at hyen [at] cs [dot] princeton [dot] edu

Thanks for checking out my website!