Projecting LLM hidden states onto F2 algebra with 42 pairs yields 93% zero-shot accuracy on logical relations and identifies prompt-preventable late-layer collapse.
Discovering latent knowledge in language models without supervision
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
extension 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
extension 1polarities
extend 1representative citing papers
Attention sharpness barely predicts VLM correctness while hidden-state probes and self-consistency strongly do, with late-fusion models showing fragile reliability bottlenecks unlike early-fusion ones.
citing papers explorer
-
Controlling Logical Collapse in LLMs via Algebraic Ontology Projection over F2
Projecting LLM hidden states onto F2 algebra with 42 pairs yields 93% zero-shot accuracy on logical relations and identifies prompt-preventable late-layer collapse.
-
Where Reliability Lives in Vision-Language Models: A Mechanistic Study of Attention, Hidden States, and Causal Circuits
Attention sharpness barely predicts VLM correctness while hidden-state probes and self-consistency strongly do, with late-fusion models showing fragile reliability bottlenecks unlike early-fusion ones.