Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
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…
cs.LG2024
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…
cs.LG2023
Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition
Zhongtian Chen, Edmund Lau, Jake Mendel +2
We investigate phase transitions in a Toy Model of Superposition (TMS) using Singular Learning Theory (SLT). We derive a closed formula for the theoretical loss and, in the case of…