SemRF supplies fixed semantic anchors and pseudo-inverse tying to produce stable coordinates for residual dynamics, Voronoi traces, and minimum-action canonical paths that link to parameter efficiency under controlled interface error.
arXiv preprint arXiv:2602.06843 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A geometric decomposition framework shows that affine transformations best recover prompt-induced task geometry and behavior in language and vision models across multiple datasets.
citing papers explorer
-
SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models
SemRF supplies fixed semantic anchors and pseudo-inverse tying to produce stable coordinates for residual dynamics, Voronoi traces, and minimum-action canonical paths that link to parameter efficiency under controlled interface error.
-
Decomposing how prompting steers behavior
A geometric decomposition framework shows that affine transformations best recover prompt-induced task geometry and behavior in language and vision models across multiple datasets.