2 papers
cs.LG2026
Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)
Hisashi Miyashita
We show that singular value decomposition of the lm_head} weight matrix of a transformer-based large language model -- requiring only five lines of PyTorch and no model inference -…
cs.LG2026
Controlling Logical Collapse in LLMs via Algebraic Ontology Projection over F2
Hisashi Miyashita, Mgnite Inc
Do large language models internally encode ontological relations in a formally verifiable algebraic structure? We introduce Algebraic Ontology Projection (AOP), which projects LLM…