English
Related papers

Related papers: Steering Language Model Refusal with Sparse Autoen…

200 papers

Large Audio-Language Models (LALMs) are becoming essential as a powerful multimodal backbone for real-world applications. However, recent studies show that audio inputs can more easily elicit harmful responses than text, exposing new risks…

Sound · Computer Science 2026-05-08 Weilin Lin , Jianze Li , Hui Xiong , Li Liu

Sparse autoencoders (SAEs) have gained a lot of attention as a promising tool to improve the interpretability of large language models (LLMs) by mapping the complex superposition of polysemantic neurons into monosemantic features and…

Computation and Language · Computer Science 2025-02-19 Gouki Minegishi , Hiroki Furuta , Yusuke Iwasawa , Yutaka Matsuo

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Computation and Language · Computer Science 2026-02-23 Mathis Le Bail , Jérémie Dentan , Davide Buscaldi , Sonia Vanier

Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the former is time-consuming and expensive, and the latter is not precisely controllable and often…

Computation and Language · Computer Science 2026-05-18 Sasha Cui , Zhongren Chen

Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and ablation. We show that this account is incomplete. Across eleven categories of refusal and…

Computation and Language · Computer Science 2026-02-03 Faaiz Joad , Majd Hawasly , Sabri Boughorbel , Nadir Durrani , Husrev Taha Sencar

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…

Computation and Language · Computer Science 2026-02-23 Joschka Braun

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Zhengxuan Wu , Jacob Steinhardt , Sarah Schwettmann

Altruism is fundamental to human societies, fostering cooperation and social cohesion. Recent studies suggest that large language models (LLMs) can display human-like prosocial behavior, but the internal computations that produce such…

General Economics · Economics 2026-04-22 Shuhuai Zhang , Shu Wang , Zijun Yao , Chuanhao Li , Xiaozhi Wang , Songfa Zhong , Tracy Xiao Liu

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt…

Computation and Language · Computer Science 2026-05-06 Geert Heyman , Frederik Vandeputte

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…

Computation and Language · Computer Science 2025-02-04 Daniel Pluth , Yu Zhou , Vijay K. Gurbani

We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retraining. We replace fragile pattern-based refusal detection…

Computation and Language · Computer Science 2026-02-25 Iker García-Ferrero , David Montero , Roman Orus

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in…

Computation and Language · Computer Science 2025-12-02 Ruben Härle , Felix Friedrich , Manuel Brack , Stephan Wäldchen , Björn Deiseroth , Patrick Schramowski , Kristian Kersting

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly…

Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of…

Machine Learning · Computer Science 2025-09-29 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Elena Tutubalina , Ivan Oseledets

Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse encoding organize the representations of activation vector from…

Machine Learning · Computer Science 2025-05-29 Wenjie Sun , Bingzhe Wu , Zhile Yang , Chengke Wu

Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based unlearning methods suffer from issues such as high computational costs, hyperparameter…

Machine Learning · Computer Science 2025-04-14 Aashiq Muhamed , Jacopo Bonato , Mona Diab , Virginia Smith

Learning hierarchical features in Sparse Autoencoders (SAEs) is essential for capturing the structured nature of real-world data and mitigating issues like feature absorption or splitting. Existing works attempt to identify hierarchical…

Machine Learning · Computer Science 2026-05-12 Tue M. Cao , Hoang X. Nhat , Raed Alharbi , Phi Le Nguyen , My T. Thai

A key challenge in interpretability is to decompose model activations into meaningful features. Sparse autoencoders (SAEs) have emerged as a promising tool for this task. However, a central problem in evaluating the quality of SAEs is the…

Machine Learning · Computer Science 2024-10-11 Constantin Venhoff , Anisoara Calinescu , Philip Torr , Christian Schroeder de Witt

Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Qing Li , Jiahui Geng , Derui Zhu , Fengyu Cai , Chenyang Lyu , Fakhri Karray
‹ Prev 1 8 9 10 Next ›