 Black-Box Access is Insufficient for Rigorous AI AuditsConference on Fairness, Accountability and Transparency (FAccT), 2024 |
 AgentBoard: An Analytical Evaluation Board of Multi-turn LLM AgentsNeural Information Processing Systems (NeurIPS), 2024 |
 Visibility into AI AgentsConference on Fairness, Accountability and Transparency (FAccT), 2024 |
 MLAgentBench: Evaluating Language Agents on Machine Learning
ExperimentationInternational Conference on Machine Learning (ICML), 2023 |
 Open-Sourcing Highly Capable Foundation Models: An evaluation of risks,
benefits, and alternative methods for pursuing open-source objectivesSocial Science Research Network (SSRN), 2023 |
 Identifying the Risks of LM Agents with an LM-Emulated SandboxInternational Conference on Learning Representations (ICLR), 2023 Yangjun Ruan Honghua Dong Andrew Wang Silviu Pitis Yongchao Zhou Jimmy Ba Yann Dubois Chris J. Maddison Tatsunori Hashimoto |
