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…
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…
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…