Cover Image

From Weights to Activations: Is Steering the Next Frontier of Adaptation?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ostermann, Simon, Gurgurov, Daniil, Baeumel, Tanja, Hedderich, Michael A., Lapuschkin, Sebastian, Samek, Wojciech, Schmitt, Vera
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sparse Subnetwork Enhancement for Underrepresented Languages in Large Language Models
by: Gurgurov, Daniil, et al.
Published: (2025)

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
by: Ghussin, Yusser Al, et al.
Published: (2026)

Modular Arithmetic: Language Models Solve Math Digit by Digit
by: Baeumel, Tanja, et al.
Published: (2025)

CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark
by: Gurgurov, Daniil, et al.
Published: (2026)

Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation
by: Gurgurov, Daniil, et al.
Published: (2025)

GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge
by: Gurgurov, Daniil, et al.
Published: (2024)

Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters
by: Gurgurov, Daniil, et al.
Published: (2024)

Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages
by: Gurgurov, Daniil, et al.
Published: (2025)

Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms
by: Baeumel, Tanja, et al.
Published: (2026)

The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs
by: Baeumel, Tanja, et al.
Published: (2025)

Multilingual Political Views of Large Language Models: Identification and Steering
by: Gurgurov, Daniil, et al.
Published: (2025)

On Multilingual Encoder Language Model Compression for Low-Resource Languages
by: Gurgurov, Daniil, et al.
Published: (2025)

Multilingual Large Language Models and Curse of Multilinguality
by: Gurgurov, Daniil, et al.
Published: (2024)

DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge
by: Ghussin, Yusser Al, et al.
Published: (2026)

From Attribution to Action: A Human-Centered Application of Activation Steering
by: Labarta, Tobias, et al.
Published: (2026)

Atlas-Alignment: Making Interpretability Transferable Across Language Models
by: Puri, Bruno, et al.
Published: (2025)

Circuit Insights: Towards Interpretability Beyond Activations
by: Golimblevskaia, Elena, et al.
Published: (2025)

Judge Circuits
by: Feldhus, Nils, et al.
Published: (2026)

The Latin Substrate: How Language Models Represent and Mediate Script Choice
by: Gurgurov, Daniil, et al.
Published: (2026)

A Close Look at Decomposition-based XAI-Methods for Transformer Language Models
by: Arras, Leila, et al.
Published: (2025)

ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance
by: Gurgurov, Daniil, et al.
Published: (2026)

The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
by: Kahardipraja, Patrick, et al.
Published: (2025)

Image-to-LaTeX Converter for Mathematical Formulas and Text
by: Gurgurov, Daniil, et al.
Published: (2024)

Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations
by: Erogullari, Eren, et al.
Published: (2025)

FADE: Why Bad Descriptions Happen to Good Features
by: Puri, Bruno, et al.
Published: (2025)

What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations
by: Trinley, Katharina, et al.
Published: (2025)

Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations
by: Dreyer, Maximilian, et al.
Published: (2023)

Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data
by: Pahde, Frederik, et al.
Published: (2025)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
by: Achtibat, Reduan, et al.
Published: (2024)

Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
by: Wang, Qianli, et al.
Published: (2024)

Iterative Inference in a Chess-Playing Neural Network
by: Sandmann, Elias, et al.
Published: (2025)

Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
by: Hatefi, Sayed Mohammad Vakilzadeh, et al.
Published: (2025)

Human-Centered Evaluation of XAI Methods
by: Dawoud, Karam, et al.
Published: (2023)

FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
by: Wang, Qianli, et al.
Published: (2025)

Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
by: Bouanani, Oussama, et al.
Published: (2026)

Steer2Edit: From Activation Steering to Component-Level Editing
by: Sun, Chung-En, et al.
Published: (2026)

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
by: Dreyer, Maximilian, et al.
Published: (2024)

Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
by: Bareeva, Dilyara, et al.
Published: (2024)

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
by: Wang, Qianli, et al.
Published: (2026)

Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
by: Wang, Qianli, et al.
Published: (2025)