pith. sign in

arXiv preprint arXiv:2602.06843 , year=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Decomposing how prompting steers behavior

cs.AI · 2026-06-02 · unverdicted · novelty 7.0

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

Showing 2 of 2 citing papers.

  • SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models cs.LG · 2026-06-30 · unverdicted · none · ref 8

    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 cs.AI · 2026-06-02 · unverdicted · none · ref 63

    A geometric decomposition framework shows that affine transformations best recover prompt-induced task geometry and behavior in language and vision models across multiple datasets.