arXiv Computation and Language November 4, 2026 By Tuc Nguyen, Marcos Guti\'errez-del-Pozo, Eduardo Paluzo-Hidalgo, Yifan Hu, Adaku Uchendu, Thai Le

TopoSteer: Topological Layer Selection for Activation Steering in LLMs

Read the original on arXiv Computation and Language →

TopoSteer introduces a topology-based method for selecting the layer at which to apply activation steering in large language models. Instead of evaluating separability or alignment, it scores layers by the total H_0 persistence of the displacement cloud, measured as the length of its Euclidean minimum spanning tree. Experiments across several models and tasks show that this approach yields more effective steering without needing held-out validation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Machine Learning

Oct 16

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment

The paper introduces Where to Steer (W2S), a framework that adaptively selects which layer of a large language model to intervene on based on the input. It argues that optimal steering layers vary across inputs and demonstrates that W2S outperforms fixed-layer steering methods on several LLMs and alignment tasks, both in‑distribution and out‑of‑distribution. The study highlights input‑dependent layer selection as a complementary design dimension to steering vector extraction.

By Soham Gadgil, Chris Lin, Su-In Lee

llms safety

arXiv AI

Aug 11

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models

arXiv:2608. 08829v1 Announce Type: cross Abstract: Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the injection layers globally per task.

By Muhammad Faishal Adly Nelwan, Alfan Farizki Wicaksono

llms rag safety

arXiv Computation and Language

2d ago

Sweep Less, Steer More: Using Activation Steering Geometry for Reduced Hyperparameter Search

The paper introduces a geometry-based metric, the discriminability index $d'$, to guide activation steering in large language models. By evaluating $d'$ across five behaviors and three models, the authors show it can reliably pinpoint effective layers for steering in multiple-choice question answering, reducing the need for exhaustive layer sweeps. While $d'$ also aids layer selection in open-ended multi-token generation, its ability to predict steering success on individual tokens is inconsistent, indicating limitations when extending from single-token to open-ended contexts.

By Nishkal Hundia, Swastik Agrawal, Navita Goyal, Sarah Wiegreffe

llms nlp

arXiv AI

Sep 15

Signatures of Steerability in Activation Space of Language Models

arXiv:2609.14151v1 Announce Type: cross Abstract: Steering language models using a set of contrastive representations has been a canonical and computationally efficient method for controlling model b...

By Prajjwal Bhattarai, Tuka Alhanai

llms safety

arXiv Machine Learning

Jun 9

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.

By Tuc Nguyen, Thai Le

llms diffusion benchmarks safety

arXiv AI

Jul 13

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.

By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

llms fine-tuning multimodal safety

One email a morning, machine-written

Related stories

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models

Sweep Less, Steer More: Using Activation Steering Geometry for Reduced Hyperparameter Search

Signatures of Steerability in Activation Space of Language Models

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs