Introduces Causal Functional Signatures grounded in causal evidence and ILP-learned architectural signatures to enable explicit, comparable, and portable mechanistic claims across model scales.
arXiv preprint arXiv:2506.09890 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
A neuron-targeted safety tuning method for VLLMs reduces attack success rates from ~20-30% to ~4-6% on average across ten languages while using less than 0.03% of parameters.
citing papers explorer
-
From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
Introduces Causal Functional Signatures grounded in causal evidence and ILP-learned architectural signatures to enable explicit, comparable, and portable mechanistic claims across model scales.
-
Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models
A neuron-targeted safety tuning method for VLLMs reduces attack success rates from ~20-30% to ~4-6% on average across ten languages while using less than 0.03% of parameters.