71 citations · 128 across the 18 of their papers we have counts for
3 papers · 1 filter
Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting
Devang Kulshreshtha, Hang Su, Haibo Jin +2
We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts o…
LiveBench: A Challenging, Contamination-Limited LLM Benchmark
Colin White, Samuel Dooley, Manley Roberts +15
Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render ben…
ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models
Benjamin Feuer, Yurong Liu, Chinmay Hegde +1
Existing deep-learning approaches to semantic column type annotation (CTA) have important shortcomings: they rely on semantic types which are fixed at training time; require a larg…