3 citations · 5 across the 17 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
When Can We Trust the Sparse Lens? A Certification Framework for SAE Faithfulness
Dibyanayan Bandyopadhyay, Asif Ekbal
Sparse autoencoders (SAEs) are increasingly used to study internal representations in language models (LMs), but it remains unclear when an SAE-based representation reliably preser…
cs.LG2026
Sparse Semantic Dimension as a Generalization Certificate for LLMs
Dibyanayan Bandyopadhyay, Asif Ekbal
Standard statistical learning theory predicts that Large Language Models (LLMs) should overfit because their parameter counts vastly exceed the number of training tokens. Yet, in p…