Dawn Song
发表论文 7 篇 · 总被引 403 次 · h-index 7
代表论文
- On the Societal Impact of Open Foundation Models (2024 · International Conference on Machine Learning · 被引 110)
- Data Shapley in One Training Run (2024 · International Conference on Learning Representations · 被引 84)
- AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies (2024 · AGI - Artificial General Intelligence - Robotics - Safety & Alignment · 被引 75)
- BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models (2024 · Conference on Empirical Methods in Natural Language Processing · 被引 68)
- AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies (2024 · arXiv.org · 被引 55)
- AutoScale: Automatic Prediction of Compute-optimal Data Composition for Training LLMs (2024 · arXiv.org · 被引 24)