collaborators

9 papers

cs.CL2026

ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety

Michael S. Lee, Yash Maurya, Drew Rein +13

Safety evaluations for large language models (LLMs) increasingly target high-stakes National Security and Public Safety (NSPS) risks, yet multilingual safety is mostly assessed thr…

cs.AI2026

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

Mubashara Akhtar, Anka Reuel, Prajna Soni +36

Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult…

cs.CL2026

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

Yu Ying Chiu, Michael S. Lee, Rachel Calcott +17

As AI systems progress, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understan…

cs.AI2026

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…

cs.CR2026

Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders

David Campbell, Neil Kale, Udari Madhushani Sehwag +5

Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures…

cs.CR2026

Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs

Jackson Kaunismaa, Avery Griffin, John Hughes +3

Model developers implement safeguards in frontier models to prevent misuse, for example, by employing classifiers to filter dangerous outputs. In this work, we demonstrate that eve…