Yu (Hope) Hou

The photo was taken by my best friend when we visited our high school in 2018. 🥰

Yu (Hope) Hou

Find me: [X] [GitHub] [LinkedIn] [Google Scholar] [Email] (houyu [at] umd [dot] edu)

Hi there! 👋

I am a second-year computer science PhD student at University of Maryland, College Park, fortunately advised by Prof. Rachel Rudinger and Prof. Hal Daumé III in the Computational Linguistics and Information Processing (CLIP) Lab. I earned my master degree from University of Southern California, where I worked with Prof. Nanyun Peng on natural language processing.

My research is in human-centered and socio-culturally aware AI. I am passionate about learning languages in social context and exploring intersections between natural language and social psychology.

More specifically, I am interested in:

(1) how AI can influence people's relationships by understanding the role language models might take under intergroup or interpersonal communication;

(2) how AI can help connect people from different cultures and communities with others by developing better and more helpful tools.

I am happy to chat about research or help with things. Feel free to reach out!

Publications

NAACL 2025

Yu Hou, Hal Daumé III and Rachel Rudinger
Who is the "other"? Language Models Predict Empathy Gaps Between Social Groups [paper]

ICLR 2025

Paola Cascante-Bonilla, Yu Hou, Yang Trista Cao, Hal Daumé III and Rachel Rudinger
Natural Language Inference Improves Compositionality in Vision-Language Models [paper] [project]

EMNLP 2023

Te-Lin Wu*, Zi-Yi Dou*, Qingyuan Hu*, Yu Hou, Nischal Chandra, Marjorie Freedman, Ralph Weischedel and Nanyun Peng
ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos [paper]

AACL 2022 (Findings)

Sunipa Dev*, Emily Sheng*, Jieyu Zhao*, Aubrie Amstutz*, Jiao Sun, Yu Hou, Mattie Sanseverino, Jiin Kim, Akihiro Nishi, Nanyun Peng and Kai-Wei Chang
On Measures of Biases and Harms in NLP [paper]

ACL 2021 (Findings)

Shikhar Singh*, Nuan Wen*, Yu Hou, Pegah Alipoormolabashi, Te-lin Wu, Xuezhe Ma and Nanyun Peng
COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences [paper] [in BIG-bench tasks]

Interspeech 2020

Qingjian Lin, Yu Hou and Ming Li
Self-Attentive Similarity Measurement Strategies in Speaker Diarization [paper]

Experience

June 2024 - Aug 2024

Research Mentor, Institute for Trustworthy AI in Law and Society (TRAILS), Summer Undergraduate Research Fellowship (SURF) Program (College Park, MD)
We worked on projects to understand the hiring experiences for people with disabilities and how AI automated interview system can be biased against them.

May 2023 - Aug 2023

Software Engineer, Flourish Science, Startup (Mountain View, CA)

Apr 2022 - Jan 2023

Software Engineer, Google, I18N NLP Localization team (Mountain View, CA)

Education

Aug 2023 - Present

University of Maryland, College Park, PhD in Computer Science

Jan 2020 - Dec 2021

University of Southern California, MSc in Computer Science

Sep 2015 - June 2019

Beijing University of Posts and Telecommunications, BSc (Eng)

Teaching

Fall 2023

Teaching Assistant for CMSC723: Natural Language Processing at University of Maryland, College Park

Fall 2021, Spring 2021

Teaching Assistant for CSCI 455x: Introduction to Programming Systems Design at University of Southern California

Fall 2019 (Session 2)

Teaching Assistant for STATS102: Introduction to Data Science at Duke Kunshan University

Service

October 31 - November 1, 2024

Co-organized AI Alignment Workshop at University of Maryland, College Park

2022 - Present

Reviewer for ACL ARR 2024 Feb/Jun/Oct, CLPsych 2024, ACL ARR 2023 Dec, EMNLP 2023, ACL 2022 Workshop CSRR