activity
20242026
most citedThe Unified Cognitive Consciousness Theory for Language Models: Anchoring Semantics, Thresholds of Activation, and Emergent Reasoning

5 citations · 7 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025★ 1 cited

Inverse-Free Wilson Loops for Transformers: A Practical Diagnostic for Invariance and Order Sensitivity

Edward Y. Chang, Ethan Y. Chang

Large language models can change answers under harmless edits that matter in practice: RAG outputs flip when passages are reordered, fine-tuning erodes invariances learned at pretr…