Nikita Haduong

qu @ cs.washington [dot] edu

I'm on the job market!

Hello!

I am a PhD Candidate in Computer Science and Engineering at the University of Washington, advised by Noah Smith. I am interested in education, creativity, and supporting human activity with thoughtful AI-assisted tools.

I received my BSOF in classical violin performance and computational linguistics at the Jacobs School of Music and was active in the indie game development scene from 2016-2023.

I chase the wind, hunt for food (ask me for highly opinionated Lists), and some of my favorite games are Furi, the Touhou series, and Bloodborne.

Teaching

I taught UW CSE481D: Games Capstone in Winter 2023 and TA'd in Spring 2021. In a mere 8 weeks, students took a game concept to publication, with multiple rounds of data-informed iteration. Check out their games!

Research

* indicates equal contribution

Raising the Stakes: Performance pressure improves AI-assisted decision making.
Nikita Haduong and Noah A. Smith.

In Submission. Paper

CPS-TaskForge: Generating collaborative problem solving environments for diverse communication tasks.
Nikita Haduong, Irene Wang, Bo-Ru Lu, Prithviraj Ammanabrolu, and Noah A. Smith.

In CustomNLP4U Workshop @ EMNLP 2024. Paper. Code.

Encode once and decode in parallel: Efficient transformer decoding.
Bo-Ru Lu, Nikita Haduong, Chien-Yu Lin, Hao Cheng, Noah A Smith, and Mari Ostendorf.

In submission. Paper

Does collaborative human–lm dialogue generation help information extraction from human–human dialogues?
Bo-Ru Lu*, Nikita Haduong*, Chia-Hsuan Lee, Zeqiu Wu, Hao Cheng, Paul Koester, Jean Utke, Tao Yu, Noah A Smith, and Mari Ostendorf.

In COLM (2024). Paper. Code.

Risks and NLP design: A case study on procedural document QA
Nikita Haduong, Alice Gao, and Noah A. Smith.

In Findings of ACL (2023). Paper.

All that's "human" is not gold: Evaluating human evaluation of generated text.
Elizabeth Clark, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan, and Noah A. Smith

In ACL (2021); Outstanding Paper award. Paper.

Multimodal alignment for affective content
Nikita Haduong*, David Nester*, Preethi Vaidyanathan, Emily Prud’hommeaux, Reynold Bailey, and Cecilia O Alm

In Workshops at AAAI (2018), Affective Content Analysis track. Paper.

IUCL at SemEval-2016 task 6: An ensemble model for stance detection in Twitter.
Can Liu, Wen Li, Bradford Demarest, Yue Chen, Sara Couture, Daniel Dakota, Nikita Haduong, Noah Kaufman, Andrew Lamont, Manan Pancholi, Kenneth Steimel, and Sandra Kübler.

In SemEval-2016. Paper.