23 citations · 23 across the 2 of their papers we have counts for
3 papers
Can CaMeLs Talk? Securing Multi-Agent Systems Against Indirect Prompt Injection Attacks
James Peters-Gill, Avi Semler, Henning Bartsch +2
Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. C…
Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks
Guillaume Corlouer, Avi Semler, Alexander Strang +1
Deep linear networks (DLNs) are used as an analytically tractable model of the training dynamics of deep neural networks. While gradient descent in DLNs is known to exhibit saddle-…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…