Metraipolis › archive › dc_164a3a006cc5

TopoSteer: Topological Layer Selection for Activation Steering in LLMs — arXiv:2611.01493

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01493
License (as archived)
CC0-1.0
Archived
2026-11-03T11:10:26.867Z
SHA-256 of the archived text
eb47ec3ecb2cafad78a3bed4a772e225a3a6979527e787e46512436ef25cbe49
Stable URL of this page
https://metraipolis.com/documento/dc_164a3a006cc5

How to cite

TopoSteer: Topological Layer Selection for Activation Steering in LLMs — arXiv:2611.01493 — arXiv (en), https://arxiv.org/abs/2611.01493 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_164a3a006cc5 (Metraipolis archive dc_164a3a006cc5, sha256 eb47ec3ecb2cafad78a3bed4a772e225a3a6979527e787e46512436ef25cbe49)
BibTeX
@misc{dc164a3a006cc5,
  title = {TopoSteer: Topological Layer Selection for Activation Steering in LLMs — arXiv:2611.01493},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01493},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_164a3a006cc5; sha256 eb47ec3ecb2cafad78a3bed4a772e225a3a6979527e787e46512436ef25cbe49},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01493. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Activation steering controls large language models at inference time by adding a vector to their internal representations. Most work asks how to build that vector, and far less attention has gone to where to add it, even though steering at a poorly chosen layer can be worse than not steering at all. Prior selectors choose a layer without ever steering the model to test it: they score how separable the target behavior is at that layer, and how consistently the individual examples point along the steering direction. We argue that what matters is not the separability of the two activation clouds, nor the alignment of individual displacements with their mean, but the extent of the cloud of per-example displacements that mean-difference steering averages. We propose a topology-based layer selection method, called TopoSteer, which scores a layer by the total H_0 persistence of its displacement cloud, computed as the length of the cloud's Euclidean minimum spanning tree. We show that the score focuses on the displacement cloud's relative geometry, while class separation affects it only through standardization. We also provide a theoretical explanation for our method by proving that, as example-level variation increases, TopoSteer and discriminability move in opposite directions, so the two criteria can rank layers in opposite ways. Across multiple language models and steering tasks, TopoSteer provides a principled alternative to discriminability- and separability-based layer selection and yields more effective steering without requiring held-out validation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.01493 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:59:52.304Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).