Yangqiu Song

Multi-step Jailbreaking Privacy Attacks on ChatGPT

2023 · 141 Zit.

Multi-step Jailbreaking Privacy Attacks on ChatGPT

2023 · 23 Zit. · arXiv (Cornell University)

From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery

2025 · 3 Zit.

From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery

2025 · 1 Zit. · ArXiv.org

Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?

2025 · 0 Zit. · ArXiv.org

OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset

2026 · 0 Zit. · arXiv (Cornell University)