Bio

Now, I'm an associate professor at ICT, CAS. Prior to joining ICT, I was an algorithm expert at Alibaba. I recieved my PhD degree from the CAS Key Lab of Network Data Science and Technology in Institute of Computing Technology, Chinese Academy of Sciences under the supervision of Prof. Jun Xu and Prof. Jiafeng Guo, and Prof. Xueqi Cheng in July 2017.
I have authored over 50 peer-reviewed publications in top-tier conferences such as ACL, WWW, and NeurIPS, as well as prestigious journals like TOIS and CSUR. Several of my works are recognized as highly cited on Google Scholar. I have also contributed as SPC or PC members over top conferences such as ACL, NeurIPS, ICML, IJCAI, AAAI and the invited reviewer for prestigious journals such as TOIS, TKDE, CSUR. I received the Best Long Paper Mention in RecSys 2019, and was selected by Stanford University as one of the World’s Top 2% Scientists in 2023 and 2024. My research interests include NLP and RecSys, particularly in safety issues in these fields.

Advertisements

We are looking for self-motivated interns/postdoc to do research with us. Feel free to contact me via email if you are interested.

2024.9
EMNLP2024

Our paper The Fall of ROME: Understanding the Collapse of LLMs in Model Editing is accepted by EMNLP2024. Congrats to Wanli!

NeurIPS2024

Our paper Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation is accepted by NeurIPS2024. Congrats to Kaike!

2024.7
RecSys2024

Three papers are accepted by RecSys2024 about safety in recommender system and contrastive leanring in gnn based recommendation. Congrats to Yuezihan, Kaike, and Yunfan!

2024.5
ACL2024

Three papers are accepted by ACL2024 about model editing, bias in knowledge conflict, and confidence alignment. Congrats to Hexiang, Wanli, and Shuchang!

2024.3
WWW2024

Our paper Unlink to Unlearn: Simplifying Edge Unlearning in GNNs is accepted by WebConf2024. Congrats to Jiajun!

2024.3
SIGIR2024

Our paper LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks is accepted by SIGIR2024. Congrats to Kaike!

Research
Interests

• Efficiently updating the knowlede/behavior of LLMs: Model Editing, Machine Unlearning
• Uncertainty/knowlede boundary of LLMs
• LLM for recommendation simulation; recommendation safety: data minimization, unlearning, membership inference, robustness

Professional
Activities

• PC Member: ICML 2022–-2024, NeurIPS 2022–-2024, ICLR2023--2024, EMNLP 2016--2024, ACL 2019--2024, SIGIR 2019--2024, WWW 2019--2024, WSDM 2021--2023, KDD 2021--2022, AAAI 2019--2024, CIKM 2020-2022,
• Senior PC: IJCAI 2021, AAAI 2022
• Reviewer: CSUR, TOIS, TKDE, TASLP, TIST, JAIR