Percy Liang

发表论文 10 篇 · 总被引 257 次 · h-index 7

代表论文

• Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models (2024 · 被引 164)
• Extracting memorized pieces of (copyrighted) books from open-weight language models (2025 · arXiv.org · 被引 38)
• BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems (2025 · Neural Information Processing Systems · 被引 37)
• Advancing Science- and Evidence-based AI Policy (2025 · Science · 被引 26)
• Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risk of Language Models (2024 · arXiv.org · 被引 24)
• Language model developers should report train-test overlap (2024 · International Conference on Machine Learning · 被引 22)