3 papers
cs.CL2026
MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang +5
This paper presents Murano, an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers…
cs.CR2026
On the Evidentiary Limits of Membership Inference for Copyright Auditing
Murat Bilgehan Ertan, Emirhan Böge, Min Chen +2
As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used duri…
cs.AI2024
Adapting the Biological SSVEP Response to Artificial Neural Networks
Emirhan Böge, Yasemin Gunindi, Erchan Aptoula +2
Neuron importance assessment is crucial for understanding the inner workings of artificial neural networks (ANNs) and improving their interpretability and efficiency. This paper in…