Jennifer Neville

LLMs Get Lost In Multi-Turn Conversation

Flipping the Dialogue: Training and Evaluating User Language Models

Beyond Similarity for Personalization: User Memory Selection via Response-Utility Optimization

DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-tuning

WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback

Lost in Transmission: When and Why LLMs Fail to Reason Globally

Node Similarities under Random Projections: Limits and Pathological Cases