Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
When Should Graph Attention Be Sparse? Learning a Per-Edge Tsallis Index
Kleyton da Costa, Bernardo Modenesi
Graph attention normalizes neighborhood scores with softmax, the maximum-entropy choice under Shannon statistics. But homophilic and heterophilic graphs want different attention sh…
cs.LG2026
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects
Seonglae Cho, Zekun Wu, Kleyton Da Costa +3
Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet whether a feature's causal role is stable across SAE families remains untested. Single-…
cs.LG2026
The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models
Seonglae Cho, Zekun Wu, Kleyton Da Costa +1
When a language model asserts that "the capital of Australia is Sydney," does it know this is wrong? Models assert misconceptions with the same fluency as facts, so the question ca…