Qinyuan Wu

Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs

In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations

Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models

Learning without Memorizing Considered Infeasible: Rethinking Memorization in LLMs

Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks

Rethinking Memorization in LLMs: On Learning by Rote vs. with Understanding