Transpose-invariant spectral diagnostics on attention operators are orientation-blind, and a φ-G two-axis diagnostic distinguishes hallucination modes with 0.62-0.84 LC-AUROC and predicted polarity reversal.
Lee, Shayan Oveis Gharan, and Luca Trevisan
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Proves high-probability exact recovery in binary CSBM after O(log n) steps of corrected normalized propagation in dense polylog regime under graph-signal and feature-SNR conditions.
GSQUEAK produces spectrally accurate sparsifiers for graph Laplacians in a single-pass distributed streaming setting.
citing papers explorer
-
Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics
Transpose-invariant spectral diagnostics on attention operators are orientation-blind, and a φ-G two-axis diagnostic distinguishes hallucination modes with 0.62-0.84 LC-AUROC and predicted polarity reversal.
-
A Spectral Theory of Normalized Corrected GNN Propagation
Proves high-probability exact recovery in binary CSBM after O(log n) steps of corrected normalized propagation in dense polylog regime under graph-signal and feature-SNR conditions.
-
Improved large-scale graph learning through ridge spectral sparsification
GSQUEAK produces spectrally accurate sparsifiers for graph Laplacians in a single-pass distributed streaming setting.