Ziang Xiao
@ziangxiao.bsky.social
assistant prof at Johns Hopkins CS
Reposted by Ziang Xiao
Congratulations to Jason Eisner, @ghadfield.bsky.social, @danielkhashabi.bsky.social, @tom-lippincott.bsky.social, Benjamin Van Durme, and @ziangxiao.bsky.social on their Discovery Awards!
CS faculty receive 2025 Johns Hopkins Discovery Awards
Winning projects—chosen from 274 proposals—include 150 individuals from across the university.
www.cs.jhu.edu
July 9, 2025 at 1:44 PM
Congratulations to Jason Eisner, @ghadfield.bsky.social, @danielkhashabi.bsky.social, @tom-lippincott.bsky.social, Benjamin Van Durme, and @ziangxiao.bsky.social on their Discovery Awards!
Reposted by Ziang Xiao
Johns Hopkins researchers including @victor-antony.bsky.social and @ziangxiao.bsky.social have created a system that could make social robots more effective at detecting and managing user interruptions—a breakthrough for areas like health care and education where natural conversation is crucial.
Talking robots learn to manage human interruptions
Johns Hopkins computer scientists designed an interruption-handling system to facilitate more natural conversations with social robots
hub.jhu.edu
August 8, 2025 at 1:33 PM
Johns Hopkins researchers including @victor-antony.bsky.social and @ziangxiao.bsky.social have created a system that could make social robots more effective at detecting and managing user interruptions—a breakthrough for areas like health care and education where natural conversation is crucial.
Reposted by Ziang Xiao
Learn more about @ziangxiao.bsky.social’s research in our new Q&A!
New faculty Q&A: Ziang Xiao
Get to know Ziang Xiao, who joins Johns Hopkins as an assistant professor of computer science.
www.cs.jhu.edu
August 18, 2025 at 1:22 PM
Learn more about @ziangxiao.bsky.social’s research in our new Q&A!
The Aug 8th deadline is only a few days away! If you have awesome HCI+NLP work to share, submit it to our workshop! sites.google.com/view/hciandnlp
🎉 Excited to announce that the 4th HCI+NLP workshop will be co-located with @emnlpmeeting.bsky.social in Suzhou, China! 🌍📍 Join us to explore the intersection of human-computer interaction and NLP. 🧵
1/
1/
August 7, 2025 at 2:09 AM
The Aug 8th deadline is only a few days away! If you have awesome HCI+NLP work to share, submit it to our workshop! sites.google.com/view/hciandnlp
We are excited to kick off the 2nd HEAL workshop tomorrow at #CHI2025. Dr. Su Lin Blodgett and Dr. Gagan Bansal from MSR will be our keynote speakers!
Welcome new and old friends! See you at G221!
All accepted papers: tinyurl.com/bdfpjcr4
Welcome new and old friends! See you at G221!
All accepted papers: tinyurl.com/bdfpjcr4
April 25, 2025 at 11:28 AM
We are excited to kick off the 2nd HEAL workshop tomorrow at #CHI2025. Dr. Su Lin Blodgett and Dr. Gagan Bansal from MSR will be our keynote speakers!
Welcome new and old friends! See you at G221!
All accepted papers: tinyurl.com/bdfpjcr4
Welcome new and old friends! See you at G221!
All accepted papers: tinyurl.com/bdfpjcr4
Reposted by Ziang Xiao
Thrilled that our paper Faux Polyglot has been accepted to #NAACL2025 main! 🚀
We show that multilingual RAG creates language-specific information cocoons and amplifies perspectives and facts in the dominant language, especially when handling knowledge conflicts.
📜 arxiv.org/abs/2407.05502
We show that multilingual RAG creates language-specific information cocoons and amplifies perspectives and facts in the dominant language, especially when handling knowledge conflicts.
📜 arxiv.org/abs/2407.05502
Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models
With Retrieval Augmented Generation (RAG), Large Language Models (LLMs) are playing a pivotal role in information search and are being adopted globally. Although the multilingual capability of LLMs of...
arxiv.org
January 31, 2025 at 3:19 PM
Thrilled that our paper Faux Polyglot has been accepted to #NAACL2025 main! 🚀
We show that multilingual RAG creates language-specific information cocoons and amplifies perspectives and facts in the dominant language, especially when handling knowledge conflicts.
📜 arxiv.org/abs/2407.05502
We show that multilingual RAG creates language-specific information cocoons and amplifies perspectives and facts in the dominant language, especially when handling knowledge conflicts.
📜 arxiv.org/abs/2407.05502
Glad to organize HEAL again at CHI2025 with a special theme of "Mind the Context"!
An awesome team of organizers: @wesleydeng.bsky.social, @mlam.bsky.social, @juhokim.bsky.social, @qveraliao.bsky.social, @cocoweixu.bsky.social, @ziangxiao.bsky.social, Motahhare Eslami, and Jekaterina Novikova!
December 17, 2024 at 9:07 PM
Glad to organize HEAL again at CHI2025 with a special theme of "Mind the Context"!
Reposted by Ziang Xiao
Had a lot of fun teaching a tutorial on Human-Centered Evaluation of Language Technologies at #EMNLP2024, w/ @ziangxiao.bsky.social, Su Lin Blodgett, and Jackie Cheung
We just posted the slides on our tutorial website: human-centered-eval.github.io
We just posted the slides on our tutorial website: human-centered-eval.github.io
Human-Centered Eval@EMNLP24
human-centered-eval.github.io
November 26, 2024 at 8:55 PM
Had a lot of fun teaching a tutorial on Human-Centered Evaluation of Language Technologies at #EMNLP2024, w/ @ziangxiao.bsky.social, Su Lin Blodgett, and Jackie Cheung
We just posted the slides on our tutorial website: human-centered-eval.github.io
We just posted the slides on our tutorial website: human-centered-eval.github.io