6 papers
The Representation-Rationalizability Tradeoff in Reward Learning
Jing Dong, Yaoliang Yu, Pascal Pourpart
In RLHF, each training example contains a prompt and two candidate responses , and annotators provide pairwise preferences between these responses. The learning problem i…
RADAR: Defending RAG Dynamically against Retrieval Corruption
Ziyuan Chen, Yueming Lyu, Yi Liu +4
While RAG systems are increasingly deployed in dynamic web search, temporal volatility amplifies their vulnerability to adversarial attacks. Existing static-oriented defenses strug…
AI in the Enterprise: How People Use M365 Copilot Chat
Scott Counts, Yan Chen, Jing Dong +9
M365 Copilot is used every week by millions of people across more than a million companies around the world as part of their workflows. Uniquely positioned in the AI landscape give…
Right-Sizing Communication and Recommendation Set Size in AI-Assisted Search
Jing Dong, Prakirt Raj Jhunjhunwala, Yash Kanoria
We model the interaction between a user and an AI driven recommendation system. The user initiates the process by conveying preference information through a costly and noisy messag…
Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems
Junli Shao, Jing Dong, Dingzhou Wang +3
With the rapid growth of Internet services, recommendation systems play a central role in delivering personalized content. Faced with massive user requests and complex model archit…
Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks
Yushang Zhao, Yike Peng, Dannier Li +3
With the rapid growth of fintech, personalized financial product recommendations have become increasingly important. Traditional methods like collaborative filtering or content-bas…