|
|
|
About
Hi! My name is Veronica Qing Lyu (吕晴). I am a Research Scientist at Databricks Mosaic Research, working on LLM agents for enterprise scenarios. Currently, I'm interested in enabling agents to continously learn from human feedback in specialized domains, with scarce data and low cost.
Previously, I obtained my PhD degree in Computer and Infomation Science from the University of Pennsylvania, and my undergraduate degree in linguistics at the Department of Foreign Languages and Literatures at Tsinghua University. My thesis research focuses on the intersection of linguistics and natural language processing, as well as interpretability of Large Language Models.
Check out our tutorial "Explanation in the Era of LLMs" (NAACL 2024)!
|
(*: equal contribution.) For a full list, see my Google Scholar profile.
MemAlign: Building Better LLM Judges From Human Feedback With Scalable Memory.
Databricks Research blog.
|
Agent Learning from Human Feedback (ALHF): A Databricks Knowledge Assistant Case Study.
Databricks Research blog.
|
Faithful and Useful Explanations by Large Language Models.
PhD thesis. [Full text]
|
Calibrating Large Language Models with Sample Consistency.
Qing Lyu*, Kumar Shridhar*, Chaitanya Malaviya, Li Zhang, Yanai Elazar, Niket Tandon, Marianna Apidianaki, Mrinmaya Sachan, Chris Callison-Burch
AAAI 2024. [paper][code]
|
Explanation-based Finetuning Makes Models More Robust to Spurious Cues
Josh Magnus Ludan, Yixuan Meng*, Tai Nguyen*, Saurabh Shah*, Qing Lyu, Marianna Apidianaki, Chris Callison-Burch
ACL 2023. [paper]
|
Faithful Chain-of-Thought Reasoning
Qing Lyu*, Shreya Havaldar*, Adam Stein*, Li Zhang, Delip Rao, Eric Wong, Marianna Apidianaki, Chris Callison-Burch
On arXiv. [paper][repo]
|
Towards Faithful Model Explanation in NLP: A Survey
Qing Lyu, Marianna Apidianaki, Chris Callison-Burch
On arXiv. [survey][outline][slides] [talk]
|
Is "my favorite new movie" my favorite movie? Probing the Understanding of Recursive Noun Phrases
Qing Lyu, Hua Zheng, Daoxin Li, Li Zhang, Marianna Apidianaki, Chris Callison-Burch
NAACL 2022. [paper][repo][bibtex][talk]
|
Zero-shot Event Extraction via Transfer Learning: Challenges and Insights
Qing Lyu, Hongming Zhang, Elior Sulem, Dan Roth
ACL 2021. [paper][repo][bibtex][talk]
|
|
