Jun Yan

About Me

I am a Research Scientist at Google Cloud AI Research. I obtained my PhD from University of Southern California (USC), advised by Prof. Xiang Ren.

My research focuses on building trustworthy Natural Language Processing (NLP) systems. Specifically, I’m interested in alignment, safety, and robustness of Large Language Models (LLMs).

You can find my CV here.

Our team is looking for student researchers to work on topics including but not limited to data synthesis, reasoning, and LLM agents. Please reach out if you are interested.

Publications

(* indicates equal contribution)

How Susceptible are Large Language Models to Ideological Manipulation?

Kai Chen, Zihao He, Jun Yan, Taiwei Shi, Kristina Lerman

EMNLP 2024 [paper] Best Paper Runner-up at SeT LLM @ ICLR 2024

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection

Jun Yan, Vikas Yadav*, Shiyang Li*, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin

NAACL 2024 [paper] [project page]

Instruction-Following Evaluation through Verbalizer Manipulation

Shiyang Li, Jun Yan, Hai Wang, Zheng Tang, Xiang Ren, Vijay Srinivasan, Hongxia Jin

Findings of NAACL 2024 [paper]

AlpaGasus: Training A Better Alpaca with Fewer Data

Lichang Chen*, Shiyang Li*, Jun Yan, Hai Wang, Kalpa Gunaratna, Vikas Yadav, Zheng Tang, Vijay Srinivasan, Tianyi Zhou, Heng Huang, Hongxia Jin

ICLR 2024 [paper] [project page]

BITE: Textual Backdoor Attacks with Iterative Trigger Injection

Jun Yan, Vansh Gupta, Xiang Ren

ACL 2023 [paper][code]

On the Robustness of Reading Comprehension Models to Entity Renaming

Jun Yan, Yang Xiao, Sagnik Mukherjee, Bill Yuchen Lin, Robin Jia, Xiang Ren

NAACL 2022 [paper][code]

RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models

Bill Yuchen Lin, Wenyang Gao, Jun Yan, Ryan Moreno, Xiang Ren

EMNLP 2021 [paper][code]

AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding

Jun Yan, Nasser Zalmout, Yan Liang, Christan Grant, Xiang Ren, Xin Luna Dong

ACL 2021 [paper]

Learning Contextualized Knowledge Structures for Commonsense Reasoning

Jun Yan, Mrigank Raman, Aaron Chan, Tianyu Zhang, Ryan Rossi, Handong Zhao, Sungchul Kim, Nedim Lipka

Findings of ACL 2021 [paper][code]

Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering

Yanlin Feng*, Xinyue Chen*, Bill Yuchen Lin, Peifeng Wang, Jun Yan, Xiang Ren

EMNLP 2020 [paper][code]

Learning from Explanations with Neural Execution Tree

Ziqi Wang*, Yujia Qin*, Wenxuan Zhou, Jun Yan, Qinyuan Ye, Leonardo Neves, Zhiyuan Liu, Xiang Ren

ICLR 2020 [paper][code]

Learning Dual Retrieval Module for Semi-Supervised Relation Extraction

Hongtao Lin, Jun Yan, Meng Qu, Xiang Ren

TheWebConf 2019 [paper][code]

Language Modeling with Sparse Product of Sememe Experts

Yihong Gu*, Jun Yan*, Hao Zhu*, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin

EMNLP 2018 [paper][code]

Preprints

(* indicates equal contribution)

Test-Time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations

Wenjie Mo, Jiashu Xu, Qin Liu, Jiongxiao Wang, Jun Yan, Chaowei Xiao, Muhao Chen

arXiv:2311.09763 [paper]

GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks

Xinlu Zhang*, Yujie Lu*, Weizhi Wang*, An Yan, Jun Yan, Lianke Qin, Heng Wang, Xifeng Yan, William Yang Wang, Linda Ruth Petzold

arXiv:2311.01361 [paper]

Honors & Awards

Sep 2019: My project receives support from Adobe Data Science Research Award ($50,000), PI: Prof. Xiang Ren
Aug 2019: Annenberg Fellowship, University of Southern California
Jul 2019: Excellent Graduate, Tsinghua University
Oct 2018: Evergrande Scholarship, Tsinghua University
Oct 2017: Samsung Scholarship, Tsinghua University
Oct 2016: JJWorld Scholarship, Tsinghua University

Education

University of Southern California

Ph.D. in Computer Science

2019 - 2024 Los Angeles, CA, U.S.

Tsinghua University

B.Eng. in Electronic Engineering

2015 - 2019 Beijing, China