Veronica Qing Lyu


Photo Credit: Haochen Zhang

Email: lyuqing [at] sas.upenn.edu

Google Scholar  |  Github  |  LinkedIn  |  CV

About

Hi! My name is Veronica Qing Lyu (吕晴). I am a fifth-year PhD student in Computer and Information Science at the University of Pennsylvania, advised by Chris Callison-Burch and Marianna Apidianaki.

In the beginning of my PhD studies, I worked on information extraction and script learning. My current research interests lie in the intersection of linguistics and natural language processing, especially probing Language Models (LMs) for interpretability. Specifically, I hope to answer three questions:

  • (i) What knowledge do LMs encode?
  • (ii) Why do LMs make certain predictions?
  • (iii) How can we make interpretability insights from (i) and (ii) actionable?
  • Before Penn, I was an undergrad in linguistics at the Department of Foreign Languages and Literatures at Tsinghua University.

    I'm co-organizing a tutorial "Explanation in the Era of LLMs" at NAACL 2024 (June 16th, 9am CST). Come check it out!

    Research

    (*: equal contribution. : undergraduate/master's mentee.)

    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
    On arXiv. [paper]
    Towards Faithful Model Explanation in NLP: A Survey
    Qing Lyu, Marianna Apidianaki, Chris Callison-Burch
    Computational Linguistics 2024. [survey][outline][slides] [talk]
    Interpretable-by-Design Text Classification with Iteratively Generated Concept Bottleneck
    Josh Magnus Ludan, Qing Lyu, Yue Yang, Liam Dugan, Mark Yatskar, Chris Callison-Burch
    On arXiv. [paper][code]
    Faithful Chain-of-Thought Reasoning
    Qing Lyu*, Shreya Havaldar*, Adam Stein*, Li Zhang, Delip Rao, Eric Wong, Marianna Apidianaki, Chris Callison-Burch
    IJCNLP-AACL 2023. [paper][repo][talk]
    Area Chair Award (Interpretability and Analysis of Models for NLP).
    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][repo]
    Representation of Lexical Stylistic Features in Language Models’ Embedding Space
    Qing Lyu, Marianna Apidianaki, Chris Callison-Burch
    *SEM 2023. [paper][repo]
    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]
    RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios
    Xinya Du, Zixuan Zhang, Sha Li, Ziqi Wang, Pengfei Yu, Hongwei Wang, Tuan Manh Lai, Xudong Lin, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Carl Vondrick, Mohit Bansal, Dan Roth, Jiawei Han, Shih-Fu Chang, Martha Palmer, Heng Ji
    NAACL 2022 demo track. [paper][repo][demo]
    Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
    A. Srivastava, …, Li Zhang, Qing Lyu, Chris Callison-Burch, … (442 authors in total)
    TMLR 2022. [paper][repo]
    Show Me More Details: Discovering Event Hierarchies from WikiHow
    Shuyan Zhou*, Li Zhang*, Yue Yang, Qing Lyu, Pengcheng Yin, Chris Callison-Burch, Graham Neubig
    ACL 2022. [paper][demo][bibtex]
    Visual Goal-Step Inference using wikiHow
    Yue Yang, Artemis Panagopoulou, Qing Lyu, Li Zhang, Mark Yatskar, Chris Callison-Burch
    EMNLP 2021.; presented at the 2nd Workshop on Advances in Language and Vision Research at NAACL 2021. [paper][bibtex]
    Goal-Oriented Script Construction
    Qing Lyu*, Li Zhang*, Chris Callison-Burch INLG 2021. [paper][repo][bibtex]
    Zero-shot Event Extraction via Transfer Learning: Challenges and Insights
    Qing Lyu, Hongming Zhang, Elior Sulem, Dan Roth
    ACL 2021. [paper][repo][bibtex][talk]
    RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System
    Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji
    NAACL 2021 demo track. [paper][repo][bibtex]
    Intent Detection with WikiHow
    Li Zhang, Qing Lyu, Chris Callison-Burch
    AACL-IJCNLP 2020. [paper][repo][bibtex][talk]
    Reasoning about goals, steps, and temporal ordering with wikihow
    Li Zhang*, Qing Lyu*, Chris Callison-Burch
    EMNLP 2020; Spotlight presentation at the Workshop on Enormous Language Models (WELM) at ICLR 2021. [paper][repo][bibtex][talk]
    Miscellaneous

    I enjoy music and street dance in my free time. I'm also a huge fan of text adventure games!

    Check out the covers by my dance crew: Ditto; Go Hard; Bloodline; Trouble Maker; 爱情36计; Lalisa; 本草纲目; 将军x以父之名.
    My guitar cover playlist in development on Youtube/Bilibili.
    I wrote a role assignment tool for playing Werewolves ("double-identity/双身份" version).