Yong Zheng-Xin

About Me

I am a third-year PhD student in the Department of Computer Science at Brown University working on multilingual foundational models, low-resource NLP, and responsible AI. I am currently advised by Prof. Stephen Bach.

I will be a research scientist intern at FAIR (Meta AI) this coming summer and fall. Before, I was part of the Responsible AI Release team of the multilingual Aya LLMs led by Sara Hooker in Cohere For AI. I also led the language adaptation research in BigScience. Before PhD, I worked on frame semantics with linguists Prof. Tiago Torrent, Prof. Oliver Czulo, and Collin F. Baker.

Research Interests

My research interests lie in developing and deploying AI technology for all language users in our multilingual society. To this end, I focus on inclusive LLMs and responsible AI, specifically:

1. building multilingual Large Language Models (LLMs) such as mT0, BLOOM and Aya,
2. supporting low-resource NLP by generating synthetic data (LexC-Gen) or parameter-efficient adaptation of pretrained LLMs (BLOOM+1), and
3. making LLMs safer and more representative for all language users. For instance, we discovered that low-resource languages can jailbreak GPT-4 and multilingual LLMs aren’t capable of code-switching.

News

• [2024/02] 🌍 Aya model and dataset papers are released! I was one of the Aya Grand Finale speakers, presenting our multilingual safety work in the Aya model paper.
• [2023/11] 🌊 Co-organized and gave the tutorial of Current Status of NLP in South East Asia at AACL 2023.
• [2023/10] 🌟 Our paper “Low-Resource Languages Jailbreak GPT-4” was accepted as the best paper at NeurIPS Socially Responsible Language Modeling (SoLaR) workshop. Also interviewed by New Scientist and featured on other media.
• [2023/09] 🤖👍 Joining the Responsible Deployment Team for Aya language model.
• [2023/07] 🪑 Serving as the Area Chair for the Multilingualism & Linguistic Diversity Track in EMNLP’23.
• [2023/06] 🐻 Passed my candidacy (in May) and released a blog post of my mid-PhD reflections.
• [2023/05] 🌊 Interviewed by Wired on our code-switching paper and grassroot research initiatve for Southeast Asian (SEA) languages.
• [2023/05] 🌸 Three multilingual papers (BLOOM+1, BLOOMZ and code-switching survey) are accepted to ACL’23!
• [2022/04] 🖼️ Our work on predicting frame shifts is accepted to LREC’22.
• [2022/03] 🌸 PromptSource paper is out and accepted to ACL’22 Demo track.
• [2022/01] 🌸 T0 paper is accepted to ICLR’22 (Spotlight) and its blog post is out.
• [2021/06] 🐻 Excited to start my PhD journey at Brown University.
• [2021/05] 🎓 Graduated from Minerva University.

Featured Publications (see all on Google Scholar)

Services

Area Chairs

• EMNLP 2023

Conference and Journal Reviewers

• ACL (2021 - 2023), EMNLP (2021)
• ACL Rolling Review (April 2022 - present)
• Springer LRE

Volunteers

• ACL 2022, ACL 2023

Mentoring

• Deep Learning Indaba
• exploreCSR 2022

Powered by Jekyll and Minimal Light theme.