arXiv Machine Learning September 2, 2026 By Beno\^it Gu\'erand, Tan Minh Nguyen

Topological Steering

Read the original on arXiv Machine Learning →

Topological Steering is a new framework that steers large language model (LLM) behavior by leveraging topological representations of activation spaces, specifically using persistence diagrams from Topological Data Analysis (TDA). Unlike traditional methods that intervene directly in activation or feature space, this approach captures global structure, making it more robust to outliers, distributional shifts, noise, and local perturbations. Experiments demonstrate that Topological Steering consistently modifies LLM behavior across multiple model families and sizes.

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 Machine Learning.

llms

arXiv Machine Learning

Jun 19

Tracking Representation Dynamics in Large Language Models with Persistent Homology

arXiv:2606. 19542v1 Announce Type: new Abstract: Large language models are commonly aligned through supervised fine-tuning, yet little is known about how their internal representations evolve during this process.

By Naman Malhotra, Jay Ambadkar, Abhinav Gupta, Kushal Kasivel, Abbas Schwarz, Kamillo Ferry, Anthea Monod

llms fine-tuning safety

arXiv Machine Learning

Aug 7

Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning

arXiv:2608. 06276v1 Announce Type: cross Abstract: Persistence diagrams (PDs) provide stable and interpretable summaries of multiscale topological structure.

By Farzana Nasrin

reinforcement-learning

arXiv AI

Jul 24

The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path

arXiv:2607. 20484v1 Announce Type: new Abstract: Large Language Models (LLMs) are fundamentally limited by representation collapse, a bottleneck that severely degrades long-context performance.

By Yiheng Tao, Kaiwen Cheng, Yao Lu, Chang Liu, Jie Chen

llms benchmarks

arXiv AI

Jun 24

Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling

arXiv:2606. 21295v2 Announce Type: replace-cross Abstract: Existing sequence models, including RNNs, LSTMs, continuous-time networks, and Transformers, share a common structural principle: layer-wise dynamics, where all neurons in the same layer co-evolve through a shared parameterized operator, leaving individual neurons no freedom to evolve independently.

By Borui Cai, Yao Zhao

llms safety

arXiv AI

Jul 10

TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Perceptual Aliasing

arXiv:2510. 04100v2 Announce Type: replace-cross Abstract: Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and protocols.

By Jiaming Wang, Jizhuo Chen, Diwen Liu, Harold Soh

benchmarks

arXiv Machine Learning

Aug 18

Look Before You Lift: Visual and Quantitative Diagnostics for Topological Deep Learning

arXiv:2608. 15388v1 Announce Type: new Abstract: Topological deep learning (TDL) methods rely on lifting raw data into higher-order discrete domains such as simplicial complexes, cell complexes, and hypergraphs.

By Mathilde Papillon, Guillermo Bern\'ardez, \'Alvaro Ball\'on Barreiro, Marco Montagna, R\'emi Devaux, Antoine Jardin, Nina Miolane

One email a morning, machine-written

Related stories

Tracking Representation Dynamics in Large Language Models with Persistent Homology

Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning

The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path

Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling

TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Perceptual Aliasing

Look Before You Lift: Visual and Quantitative Diagnostics for Topological Deep Learning