LANCE: Exploration and Reflection for LLM-based Textual Attacks on News Recommendation
A reflection-driven and exploration-oriented textual attack framework revealing vulnerabilities in news recommender systems.
✈️Yuyue Zhao
Researcher in Recommender Systems & Trustworthy AI
Professional Summary
I am a researcher in recommender systems and trustworthy AI. I completed my PhD in Computer Science at the University of Amsterdam, advised by Prof. dr. Maarten de Rijke. Before that, I worked with Prof. dr. Xiangnan He and Prof. dr. Xiang Wang.
My work focuses on generative recommendation, LLM agents for recommendation, and the safety and robustness of recommender systems, especially in sensitive domains such as news recommendation and personalized content delivery, where user trust and experience are critical.
I successfully defended my Ph.D. thesis titled From enhancement to exploitation: The dual role of LLMs in recommender systems on 23rd Oct 2025. I am looking for positions to continue my career.
Education
PhD in Computer Science
University of Amsterdam
Combined M.E.–Ph.D. Program in Computer Science
University of Science and Technology of China
B.E. in Communication Engineering
Southwest Jiaotong University
Interests
Generative Recommendation
LLM Agents for Recommendation
Trustworthy Recommendation
News Recommendation & Media Bias
Featured Publications
Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning
ToolRec uses LLM agent and conduct tool-learning to achieve controllable, interpretable, and aligned recommendations.
Recent Publications
(2025).
LANCE: Exploration and Reflection for LLM-based Textual Attacks on News Recommendation.
19th ACM Conference on Recommender Systems (RecSys), Spotlight Oral.
(2025).
EvoWiki: Evaluating LLMs on Evolving Knowledge.
63rd Annual Meeting of the Association for Computational Linguistics (ACL).
(2025).
Revisiting Language Models in Neural News Recommender Systems.
47th European Conference on Information Retrieval (ECIR).
(2024).
A+B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential.
62nd Annual Meeting of the Association for Computational Linguistics (ACL).
(2024).
Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning.
47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR).