5 papers
Muse Spark Safety & Preparedness Report
Cristina Menghini, Peter Ney, Hamza Kwisaba +117
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 Framewo…
LLM Novice Uplift on Dual-Use, In Silico Biology Tasks
Chen Bo Calvin Zhang, Christina Q. Knight, Nicholas Kruus +16
Large language models (LLMs) perform increasingly well on biology benchmarks, but it remains unclear whether they uplift novice users -- i.e., enable humans to perform better than…
Search-Time Data Contamination
Ziwen Han, Meher Mankikar, Julian Michael +1
Data contamination refers to the leakage of evaluation data into model training data, resulting in overfitting to supposedly held-out test sets and compromising test validity. We i…
FORTRESS: Frontier Risk Evaluation for National Security and Public Safety
Christina Q. Knight, Kaustubh Deshpande, Ved Sirdeshmukh +4
The rapid advancement of large language models (LLMs) introduces dual-use capabilities that could both threaten and bolster national security and public safety (NSPS). Models imple…
A Red Teaming Roadmap Towards System-Level Safety
Zifan Wang, Christina Q. Knight, Jeremy Kritz +2
Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine…