4 papers · 1 filter
Did the LLM Answer the Question? A Semantic Reconstruction Game for Jailbreak Evaluation
Liam Davis, Romain Emil-Popescu, Suman Jana
Jailbreak attacks against large language models (LLMs) are evaluated using attack success rate (ASR), which depends on correctly identifying responses that fulfill prohibited reque…
Learning Lookahead Lemmas for Neural Network Verification
Liam Davis, Haoze Wu
State-of-the-art neural network verifiers use the branch-and-bound procedure as their core solving mechanism. We introduce an inprocessing framework for neural network verification…
Lookahead Branching for Neural Network Verification
Liam Davis, Duo Zhou, Huan Zhang +3
In this work, we investigate the effect of lookahead branching strategies in neural network verification. We present a general recipe to integrate lookahead into any branch-and-bou…
Lattice Deduction Transformers
Liam Davis, Leopold Haller, Alberto Alfarano +1
We introduce the Lattice Deduction Transformer (LDT), a recurrent transformer that approximates logically sound deduction by projecting its latent state through a lattice between f…