arXiv Machine Learning July 9, 2026 By Maximilian S. Ernst (Max Planck School of Cognition, Center for Lifespan Psychology Max Planck Institute for Human Development, Machine Learning Group Technische Universit\"at Berlin), Lorenz Linhardt (Machine Learning Group Technische Universit\"at Berlin, Berlin Institute for the Foundations of Learning and Data), Aaron Peikert (Center for Lifespan Psychology Max Planck Institute for Human Development), Oliver Eberle (Machine Learning Group Technische Universit\"at Berlin, Berlin Institute for the Foundations of Learning and Data)

Distributed Sparse Interventions in Language Models

Read the original on arXiv Machine Learning →

arXiv:2607. 07128v1 Announce Type: new Abstract: Language models perform a wide range of tasks at varying levels of abstraction with the capacity to flexibly infer tasks from context, execute multiple tasks simultaneously, and select among competing tasks.

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

Aug 7

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

arXiv:2608. 05732v1 Announce Type: new Abstract: Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment.

By Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad, Ali Abbasi, Seyedarmin Azizi

llms safety

arXiv Computation and Language

3d ago

MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation

MetaSteer is a new method for steering large language models that learns nonlinear, context-dependent interventions applied to attention projection matrices. Unlike traditional linear, context-independent techniques, MetaSteer adapts its effects based on the input, requiring no linear concept-geometry assumption. Trained once on a pooled preference corpus, it transfers zero‑shot to unseen concepts and out‑of‑distribution contexts, matching or surpassing strong task‑specific baselines on multiple benchmarks and model families.

By Mehdi Jafari, Hao Xue, Flora Salim

llms agents benchmarks safety

arXiv Machine Learning

Aug 11

Large language models reorganize representational geometry during in-context learning

arXiv:2605. 28854v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit remarkable flexibility in adapting to novel tasks from in-context examples without parameter updates, a capability known as in-context learning (ICL).

By Hua-Dong Xiong, Li Ji-An, Robert C. Wilson, Kwonjoon Lee, Xue-Xin Wei

llms

arXiv Machine Learning

Jun 16

High-Dimensional Random Projection for Activation Steering in Language Models

arXiv:2606. 15092v1 Announce Type: new Abstract: Activation steering has emerged as a key methodology for controlling the behavior of large language models (LLMs).

By Minh-Hieu Pham, Bach Do, Laziz Abdullaev, Tan Minh Nguyen, Khoat Than

llms benchmarks

arXiv AI

Jul 3

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

arXiv:2607. 02460v1 Announce Type: cross Abstract: Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain.

By Zhuowei Chen, Xiang Lorraine Li

llms reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jun 12

Language Model Circuits Are Sparse in the Neuron Basis

arXiv:2601. 22594v2 Announce Type: replace-cross Abstract: The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986).

By Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt, Sarah Schwettmann

llms benchmarks safety

One email a morning, machine-written

Related stories

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation

Large language models reorganize representational geometry during in-context learning

High-Dimensional Random Projection for Activation Steering in Language Models

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

Language Model Circuits Are Sparse in the Neuron Basis