Adam Khoja

发表论文 12 篇 · 总被引 1005 次 · h-index 8

代表论文

• The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning (2024 · International Conference on Machine Learning · 被引 510)
• A benchmark of expert-level academic questions to assess AI capabilities (2025 · Nature · 被引 373)
• Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? (2024 · Neural Information Processing Systems · 被引 82)
• Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs (2025 · Neural Information Processing Systems · 被引 68)
• The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems (2025 · arXiv.org · 被引 50)
• A Definition of AGI (2025 · arXiv.org · 被引 34)