Skip to content
AI Atlas
PaperActive

GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models

arxiv.org/abs/2609.10658

quality89

Updated 2 h ago · first seen 11 Sept 2026

paper_01M294FNR3EX7ZFP8XA5MR6HEW

Published
11 Sept 2026
T1 · 2 h ago
arXiv
2609.10658
T1 · 2 h ago
Category
cs.LG
T1 · 2 h ago

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

9 claims · 9 properties

Official pageofficial_url1

Claim history for Official page
ValueValid from → toStatusSourceConfidenceExtractor
https://arxiv.org/abs/2609.10658currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Abstractabstract1

Claim history for Abstract
ValueValid from → toStatusSourceConfidenceExtractor
Activation steering provides a lightweight way to control large language models (LLMs) by modifying their hidden activations at inference time. Among these approaches, norm-preserving steering aims to change model behavior without altering the activation norm, reducing the risk of representation collapse and degradation. However, existing norm-preserving methods are limited by predefined steering trajectories and by their reliance on one-step updates, which may fail to capture the complex structure of activation distributions. We propose GeoSteer, an optimization-based method for norm-preserving activation steering. GeoSteer formulates steering as a Riemannian optimization problem and updates activations through a sequence of small geodesic steps on the representation manifold. To avoid fixed steering directions, GeoSteer learns a nonlinear activation-space objective that distinguishes desired from undesired activations, and uses this function to adaptively guide each steering step. This multistep formulation yields smoother, more stable, and more consistent steering behavior while preserving the activation norm. Across TruthfulQA, RealToxicityPrompts, and UltraFeedback benchmarks, GeoSteer consistently improves over state-of-the-art activation steering baselines. These results suggest that norm-preserving steering can be made more effective by replacing predefined one-step edits with adaptive, geometry-aware optimization.currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Arxiv announce typearxiv_announce_type1

Claim history for Arxiv announce type
ValueValid from → toStatusSourceConfidenceExtractor
newcurrentcurrentarXiv (Atom API + RSS)T1highdeterministic

arXiv idarxiv_id1

Claim history for arXiv id
ValueValid from → toStatusSourceConfidenceExtractor
2609.10658currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Authorsauthors1

Claim history for Authors
ValueValid from → toStatusSourceConfidenceExtractor
Xuan Cuong Ngo, Hao Vo, Ngan LecurrentcurrentarXiv (Atom API + RSS)T1highdeterministic

Categoriescategories1

Claim history for Categories
ValueValid from → toStatusSourceConfidenceExtractor
cs.LGcurrentcurrentarXiv (Atom API + RSS)T1highdeterministic

PDFpdf_url1

Claim history for PDF
ValueValid from → toStatusSourceConfidenceExtractor
https://arxiv.org/pdf/2609.10658currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Primary categoryprimary_category1

Claim history for Primary category
ValueValid from → toStatusSourceConfidenceExtractor
cs.LGcurrentcurrentarXiv (Atom API + RSS)T1highdeterministic

Publishedpublished_at1

Claim history for Published
ValueValid from → toStatusSourceConfidenceExtractor
11 Sept 2026currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →