5 papers
SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings
Yingjie Wang, Yi Dong, Edmund Lau +3
Rare events govern the safety profile of modern AI systems, yet their probabilities are extremely difficult to estimate: direct Monte Carlo requires prohibitive sample budgets. Sub…
Boundary Point Jailbreaking of Black-Box LLMs
Xander Davies, Giorgi Giglemiani, Edmund Lau +3
Frontier LLMs are safeguarded against attempts to extract harmful information via adversarial prompts known as "jailbreaks". Recently, defenders have developed classifier-based sys…
Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
Einar Urdshals, Edmund Lau, Jesse Hoogland +2
We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through…
Estimating the Local Learning Coefficient at Scale
Zach Furman, Edmund Lau
The \textit{local learning coefficient} (LLC) is a principled way of quantifying model complexity, originally derived in the context of Bayesian statistics using singular learning…
The Local Learning Coefficient: A Singularity-Aware Complexity Measure
Edmund Lau, Zach Furman, George Wang +2
The Local Learning Coefficient (LLC) is introduced as a novel complexity measure for deep neural networks (DNNs). Recognizing the limitations of traditional complexity measures, th…