Amazon Web Services (Applied Scientist Intern)

Explore zero-shot performance across a variety of large language models, develop cross-domain training method, and partner with data linguist team to produce and evaluate a dataset for query-based multi-document summarization (containing questions, summaries, and clusters of source documents) (Comprehend Team).

Google (Software Engineering Intern)

Design clustering and ranking algorithm to display top user-submitted review images for Shopping; analyze image data and propose signal thresholds to identify low-quality images (Google Shopping and Pointer Content Understanding Teams).

Google (Software Engineering Intern)

Implement hierarchical RNN models in Tensorflow to predict dialogue act labels with BERT embeddings (DialogFlow Team).

Google (Software Engineering Intern)

Build image carousel for displaying relevant images in Google Search event cards (Events Search Team).

Interactive Figure-Text Integration at Document Scale

Alyssa Hwang, Hita Kambhamettu, Yue Yang, Ajay Patel, Joseph Chee Chang, Andrew Head.

In preparation.

Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers

Hita Kambhamettu, Alyssa Hwang, Philippe Laban, Andrew Head.

arXiv preprint (in submission)

RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors

Liam Dugan, Alyssa Hwang, Filip Trhlík, Josh Magnus Ludan, Andrew Zhu, Hainiu Xu, Daphne Ippolito, Chris Callison-Burch.

Association for Computational Linguistics 2024

FanOutQA: Multi-Hop, Multi-Document Question Answering for Large Language Models

Andrew Zhu, Alyssa Hwang, Liam Dugan, Chris Callison-Burch.

Association for Computational Linguistics 2024

Ivie: Lightweight Anchored Explanations of Just-Generated Code

Litao Yan, Alyssa Hwang, Zhiyuan Wu, Andrew Head.

ACM Conference on Human Factors in Computing Systems 2024

NewsQs: Multi-Source Question Generation for the Inquiring Mind

Alyssa Hwang, Kalpit Dixit, Miguel Ballesteros, Yassine Benajiba, Vittorio Castelli, Markus Dreyer, Mohit Bansal, Kathleen McKeown.

arXiv preprint

Work conducted during an internship at AWS AI Labs.

Grounded Intuition of GPT-Vision's Abilities with Scientific Figures

Alyssa Hwang, Andrew Head, Chris Callison-Burch.

arXiv preprint

Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications

Andrew Zhu*, Liam Dugan*, Alyssa Hwang, Chris Callison-Burch.

Workshop for Natural Language Processing Open-Source Software (co-located with EMNLP)

Large Language Models as Sous Chefs: Revising Recipes with GPT-3

Alyssa Hwang*, Bryan Li*, Zhaoyi Hou*, Dan Roth.

arXiv preprint

Rewriting the Script: Adapting Text Instructions for Voice Interaction

Alyssa Hwang, Natasha Oza, Chris Callison-Burch, Andrew Head.

ACM Conference on Designing Interactive Systems

QuakerBot: A Household Dialog System Powered by Large Language Models

Artemis Panagopoulou, Manni Arora, Li Zhang, Dimitri Cugini, Weiqiu You, Yue Yang, Liyang Zhou, Yuxuan Wang, Zhaoyi Hou, Alyssa Hwang, Lara Martin, Sherry Shi, Chris Callison-Burch, Mark Yatskar.

Alexa Prize Taskbot Proceedings

Towards Augmenting Lexical Resources for Slang and African American English

Alyssa Hwang, William R. Frey, and Kathleen McKeown.

Workshop on NLP for Similar Languages, Varieties and Dialects (co-located with COLING)

AMPERSAND: Argument Mining for PERSuAsive oNline Discussions

Tuhin Chakrabarty, Christopher Hidey, Smaranda Muresan, Kathy McKeown, Alyssa Hwang.

Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing

Confirming the Non-compositionality of Idioms for Sentiment Analysis

Alyssa Hwang, Christopher Hidey.

Joint Workshop on Multiword Expressions and WordNet (co-located with ACL)

The Ethics Institute at Kent Place School

Rethinking Ethical Behavior for Oneself Online Together (REBOOT) assembly

Authorship Matters in Generative AI

Google People and AI Research (PAIR) Machine Learning

A Principled Approach to Developing Grounded Intuition of Generative Models

Columbia University Natural Language Processing Seminar

Rewriting the Script: Human-Centered Opportunities for Natural Language Processing

Women in Data Science @ Penn

Human-centered AI Research and Design

University of Pennsylvania Computational Linguistics Lunch (CLunch)

Developing Grounded Intuition of Large Language Models

University of Pennsylvania Computational Linguistics Lunch (CLunch)

Rewriting the Script: Adapting Text Instructions for Voice Interaction

AI's Hidden Challenges: A Conversation with Alyssa Hwang

Season 3 Episode 4, Tapping In podcast .

Wider Perspectives

Laura J. Cole, Kent Place Magazine (cover story) .

A Peak into the Future of Visual Data Interpretation

Nathi Magubane, Penn Today.

ChatGPT-Maker OpenAI Hosts its First Big Tech Showcase as the AI Startup Faces Growing Competition

Barbara Ortutay and Matt O'Brien, Associated Press.

Reposted by 162 US news outlets, including The Independent, ABC News, Washington Post, U.S. News & World Report, The Business Journal, and CBS News.

As OpenAI's Multimodal API Launches Broadly, Research Shows It's Still Flawed

Kyle Wiggers, TechCrunch.

Rewriting the Script: Developing Effective AI Assistants

Alyssa Hwang, Penn Engineering Today.

Doctorates do Valentines!

Ebonee Johnson, Official Blog of the Penn Dept. of Computer and Information Science.

Mialy Rasetarinera (Penn CIS PhD Mentorship Program)

Matthew Burke, Ryan Hsing-Smith, Bryan Yao, Joseph Koo, Sebastian Lee, Zachary Arnold (Undergraduate Senior Design Project)

Juni Kim (High School Independent Study)

Jasmine Chen (Undergraduate Thesis)

University of Pennsylvania Dept. of Computer and Information Science

Invited Panelist, PhD New Student Orientation

MindCORE Diversity and Equity Initiative (DivE In)

Invited Speaker, Overview of the PhD Application Process

University of Pennsylvania School of Engineering and Applied Science

Invited Panelist, PhD Open House

ACM Capital Region Celebration of Women in Computing (CAPWIC)

Invited Panelist, Graduate School: Is It Right for Me?

University of Pennsylvania School of Engineering and Applied Science

Invited Panelist, Graduate Recruitment Panel

University of Pennsylvania School of Engineering and Applied Science

Invited Panelist, PhD Open House

Columbia University Department of Computer Science

Invited Speaker, Alumni-In-Residence Discussion

Founder, Penn CIS PhD Mentorship Program

Co-Chair, Computer and Information Science Doctoral Association (CISDA)

Advocate for student interests and liaise with faculty of CIS and Penn Engineering.

PhD representative, Department of Computer and Information Science Office Committee

PhD representative, Penn Engineering Dean's Doctoral Advisory Board

Co-organizer, Penn NLP Computational Linguistics Lunch (CLunch)

Co-organizer, MindCORE Diversity and Equity Initiative (DivE In)

Programming Development Committee Lead, Steering Committee Member

Collaborate across departments to establish inaugural DivE In, a fully funded weekend of workshops for underrepresented undergraduates in the mind sciences.