Siqi Wang

Principles and Practices of Real-Time Feature Computing Platforms for ML

2023 · Communications of the ACM

No abstract available.

CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference

2024 · arXiv (Cornell University)

As large language models (LLMs) constantly evolve, ensuring their safety remains a critical research problem. Previous red-teaming approaches for LLM safety have primarily focused on single prompt attacks or goal hijacking. To the best of …