paper-with-me

홈 › Papers

Muse Spark Safety & Preparedness Report

2026-05-14 · Cristina Menghini, Peter Ney, Hamza Kwisaba, Zifan, Wang, Miles Turpin, Felix Binder, Jean-Christophe Testud, Aidan Boyd, Nathaniel Li, Ivan Evtimov, Klaudia Krawiecka, Arman Zharmagambetov, Jeremy Kritz, Alexander R. Fabbri, Daniel Song, Jinpeng Miao, Joonas Hjelt, Meghna Ramani, Leona Lan, Reza Aghajani, Joanna Bitton, Mahesh Pasupuleti, Devin Norder, Khalid El-Arini, Paridhi Singh, Vítor Albiero, Sahana CB, Rashnil Chaturvedi, Elahe Dabir, Edoardo Debenedetti, Jim Gust, Ziwen Han, Kat He, Sean Hendryx, Lifeng Jin, Polina Kirichenko, Sandra Lefdal, Kenneth Li, Asad Liaqat, Inna Lin, Despoina Magka, Neal Mangaokar, Ishita Mediratta, Zach Miller, Smitha Milli, Niloofar Mireshghallah, Saba Nazir, Hung Nguyen, Maximilian Nickel, Kelvin Niu, Kerem Oktar, Bhargavi Paranjape, Parth Pathak, Maya Pavlova, Emmanuel Ramirez, David Renardy, Candace Ross, Yasha Sheynin, Claudia Shi, Shivam Singhal, Evangelia Spiliopoulou, Rakshith Sharma Srinivasa, Jamelle Watson-Daniels, Spencer Whitman, Adina Williams, Chen Xing, Andy Zou, Tommy Ma, Siqi Deng, James Beldock, Prashant Ratanchandani, Kate Plawiak, Taesung Lee, Ryan Victory, Lindsay Hundley, Rachad Alao, Himaghna Bhattacharjee, Jianfeng Chi, Gary Frost, Pegah Ghahremani, Niki Howe, Yuheng Huang, Saeed Jahed, Hannah Korevaar, Trang Le, Zhe Liu, Jinghong Luo, Qin Lyu, Nina Mehrabi, Abraham Montilla, Chirag Nagpal, Cyrus Nikolaidis, Rajvardhan Oak, Manoj Ravi, Vidya Sarma, Aman Shankar, Alana Shine, Eric Michael Smith, Mariana Tandon, Michael Tontchev, Caoyu Wang, Zihan Wang, Corinne Wong, Zheng Wu, Hongyuan Zhan, Justin Zhao, Zexuan Zhong, Chengxu Zhuang, Tristan Goodman, Ayaz Minhas, Harrison Rudolph, Victoria Jeffries, Ingrid Dickinson, Alex Vaughan, Lauren Deason, Kamalika Chaudhuri, Julian Michael, Shengjia Zhao, Summer Yue arxiv

Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framework, along with the evidence that informed our launch decision. We then discuss additional considerations, such as Muse Spark's broader content safety and behavioral profile, that are relevant to overall safety but fall outside the catastrophic risk domains governed by the Framework. Our preparedness results covering Chemical and Biological, Cybersecurity, and Loss of Control risks assess Muse Spark's deployment within Meta AI as presenting acceptable levels of residual risks under our Advanced AI Scaling Framework. We conducted a broad set of evaluations targeting dual-use and high-risk capabilities across these catastrophic risk domains. Those evaluations identified elevated risks prior to mitigations, with Chemical and Biological capabilities assessed as likely reaching the "high risk" category under the Advanced AI Scaling Framework before safeguards were applied. We have implemented a multi-layered set of mitigations that address the identified risks, and Muse Spark demonstrates state-of-the-art refusal across a range of benchmarks related to hazardous workflows in chemistry and biology. We therefore release Muse Spark as the underlying model of Meta AI.

📄 PDF Abstract BibTeX arXiv:2606.12429

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

APEX-Accounting

2026-07-29 · Julien Benchek, Austin Bennett, Jasmin Kern, Ryan Stevens 외 arxiv

We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountants. Tasks include reconciling accounts, accruing expenses, posting tr…

Model Capability Assessment and Safeguards for Biological Weaponization

2026-04-15 · Michael Richter arxiv

AI leaders and safety reports increasingly warn that advances in model reasoning may enable biological misuse, including by low-expertise users, while major labs describe safeguards as expanding but still evolving rather…

MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models

2025-09-18 · Siyu Yan, Long Zeng, Xuecheng Wu, Chengcheng Han 외 arxiv

As large language models~(LLMs) become widely adopted, ensuring their alignment with human values is crucial to prevent jailbreaks where adversaries manipulate models to produce harmful content. While most defenses targe…

Red Teaming

Code World Model Preparedness Report

2026-05-01 · Daniel Song, Peter Ney, Cristina Menghini, Faizan Ahmad 외 arxiv

This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conducted pre-release testing across domains identified in our Frontier AI F…

Code Generation

OpenAI o1 System Card

2024-12-21 · OpenAI, :, Aaron Jaech, Adam Kalai 외

The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In…

ManagementRed Teaming