Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
Akira Ito, Masanori Yamada, Daiki Chijiwa +1
Recently, Ainsworth et al. empirically demonstrated that, given two independently trained models, applying a parameter permutation that preserves the input-output behavior allows t…
cs.CL2025
Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
Tomoya Yamashita, Akira Ito, Yuuki Yamanaka +3
As large language models (LLMs) are increasingly deployed across various applications, privacy and copyright concerns have heightened the need for more effective LLM unlearning tec…