Yukun Zhao

· Mobile: (+86) 17615832193 Email: yukunzhao.sdu@gmail.com

EDUCATION

Shandong University , School of Computer Science and Technology, Ph.D. 2020.09 - 2024.09 Shandong University , School of Computer Science and Technology, M.S. 2014.09 - 2017.06 Northeastern University , School of Software, B.S. 2010.09 - 2014.06

CAREER

Shandong University , School of Artificial Intelligence, Associate Professor, 2025.12 - Now

Baidu Inc. , Search Strategy Department, Staff Engineer, 2020.09 - 2025.12

Alibaba Group , Recommendation Algorithm Department, Senior Engineer, 2019.04 - 2020.09

JD.com, Inc. , Recommendation Algorithm Department, Engineer, 2017.06 - 2019.04

Baidu Inc. , Search Algorithm Department, Intern, 2016.09 - 2017.01

Microsoft Research Asia (MSRA) , NLP Computing Group, Intern, 2016.05 - 2016.08

PUBLICATIONS

Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning. Yukun Zhao , Lingyong Yan, Zhenyang Li, Shuaiqiang Wang, Zhumin Chen, Zhaochun Ren, Dawei Yin. Submitted to IPM (CCF B) .
Task Knowledge Injection via Interpolations and Reinstatement for Large Language Model Generalization. Yukun Zhao , Lingyong Yan, Zhenyang Li, Shuaiqiang Wang, Zhumin Chen, Zhaochun Ren, Dawei Yin. ACL 2025 (CCF A)
Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method. Yukun Zhao , Lingyong Yan, Weiwei Sun, Guoliang Xing, Shuaiqiang Wang, Chong Meng, Zhicong Cheng, Zhaochun Ren, Dawei Yin. NAACL 2024 (CCF B, TH-CPL A)
Improving the Robustness of Large Language Models via Consistency Alignment. Yukun Zhao , Lingyong Yan, Weiwei Sun, Guoliang Xing, Shuaiqiang Wang, Chong Meng, Zhicong Cheng, Zhaochun Ren, Dawei Yin. COLING 2024 (CCF B)
DiQAD: A Benchmark Dataset for Open-domain Dialogue Quality Assessment. Yukun Zhao , Lingyong Yan, Weiwei Sun, Chong Meng, Shuaiqiang Wang, Zhicong Cheng, Zhaochun Ren, Dawei Yin. EMNLP 2023 (CCF B, TH-CPL A)
Explainable User Clustering in short text streams. Yukun Zhao , Shangsong Liang, Zhaochun Ren, Jun Ma, Emine Yilmaz, Maarten de Rijke. SIGIR 2016 (CCF A)
Personalized Re-ranking of Tweets. Yukun Zhao , Shangsong Liang, Jun Ma. WISE 2016 (CCF B)
VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization. Dongsheng Zhu, Xunzhu Tang, Weidong Han, Jinghui Lu, Yukun Zhao , Guoliang Xing, Junfeng Wang, Dawei Yin. NAACL 2024 (CCF B, TH-CPL A)
Feature-level Debiased Natural Language Understanding. Yougang Lyu, Piji Li, Yechang Yang, Maarten de Rijke, Pengjie Ren, Yukun Zhao , Dawei Yin, Zhaochun Ren. AAAI 2023 (CCF A)
Inferring Dynamic User Interests in Streams of Short Texts for User Clustering. Shangsong Liang, Zhaochun Ren, Yukun Zhao , Jun Ma, Emine Yilmaz, Maarten De Rijke. In TOIS 2017 (CCF A)

Seven of the ten papers are first-authored, with six of them already accepted.
Papars 1 to 4 address forgetting, generalization, hallucination and robustness in LLMs. Paper 8 focuses on instruction optimization in MLLMs. Paper 5 presents a dialogue quality assement ben- — chamark while Paper 9 deals with debiasing in traditional LMs. The remaining papers 6, 7, and 10 — are on topic modeling.

PATENTS

A method, Apparatus, System, and Storage Medium for Dispatching Orders with Questions. Bai -cheng Chen, Yizhi Jiang, Yukun Zhao , Guoliang Xing, Zhicong Cheng . Chinese Invention Patent (First-Class Patent) No. CN117610850A.
A Training Method for Multi-turn Dialogue Quality Assessment. Shanshan Zhao, Hongyu Li, Yukun Zhao , Guoliang Xing, Zhicong Cheng . Chinese Invention Patent No. CN117556005A.