English
Related papers

Related papers: Model Unlearning via Sparse Autoencoder Subspace G…

200 papers

The rapid advancement of Large Language Models (LLMs) has demonstrated their vast potential across various domains, attributed to their extensive pretraining knowledge and exceptional generalizability. However, LLMs often encounter…

Computation and Language · Computer Science 2024-06-06 Zheyuan Liu , Guangyao Dou , Zhaoxuan Tan , Yijun Tian , Meng Jiang

Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…

Machine Learning · Computer Science 2025-05-26 Wei Shi , Sihang Li , Tao Liang , Mingyang Wan , Guojun Ma , Xiang Wang , Xiangnan He

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Machine Learning · Computer Science 2026-03-17 Thibault Formal , Maxime Louis , Hervé Dejean , Stéphane Clinchant

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Enrico Cassano , Riccardo Renzulli , Marco Nurisso , Mirko Zaffaroni , Alan Perotti , Marco Grangetto

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Machine Learning · Computer Science 2025-08-14 Charles O'Neill , Mudith Jayasekara , Max Kirkby

Recent work shows that Sparse Autoencoders (SAE) applied to large language model (LLM) layers have neurons corresponding to interpretable concepts. These SAE neurons can be modified to align generated outputs, but only towards…

Computation and Language · Computer Science 2025-07-01 Ananya Joshi , Celia Cintas , Skyler Speakman

The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper presents a novel framework that leverages sparse autoencoders…

Machine Learning · Computer Science 2025-02-18 Zirui He , Haiyan Zhao , Yiran Qiao , Fan Yang , Ali Payani , Jing Ma , Mengnan Du

The widespread popularity of Large Language Models (LLMs), partly due to their unique ability to perform in-context learning, has also brought to light the importance of ethical and safety considerations when deploying these pre-trained…

Computation and Language · Computer Science 2024-08-07 Karuna Bhaila , Minh-Hao Van , Xintao Wu

In recent years, unlearning techniques, which are methods for inducing a model to "forget" previously learned information, have attracted attention as a way to address privacy and copyright concerns in large language models (LLMs) and large…

Machine Learning · Computer Science 2025-10-29 Tatsuki Kawakami , Kazuki Egashira , Atsuyuki Miyai , Go Irie , Kiyoharu Aizawa

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Machine Learning · Computer Science 2026-02-03 Jack Gallifant , Shan Chen , Kuleen Sasse , Hugo Aerts , Thomas Hartvigsen , Danielle S. Bitterman

Although Multimodal Large Language Models (MLLMs) have advanced substantially, they remain vulnerable to object hallucination caused by language priors and visual information loss. To address this, we propose SAVE (Sparse Autoencoder-Driven…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Sangha Park , Seungryong Yoo , Jisoo Mok , Sungroh Yoon

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…

Machine Learning · Computer Science 2025-09-24 Dong Shu , Xuansheng Wu , Haiyan Zhao , Daking Rai , Ziyu Yao , Ninghao Liu , Mengnan Du

Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are…

Artificial Intelligence · Computer Science 2026-01-08 Yi Fang , Wenjie Wang , Mingfeng Xue , Boyi Deng , Fengli Xu , Dayiheng Liu , Fuli Feng

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows…

Machine Learning · Computer Science 2025-01-31 Gonçalo Paulo , Nora Belrose

Machine unlearning empowers individuals with the `right to be forgotten' by removing their private or sensitive information encoded in machine learning models. However, it remains uncertain whether MU can be effectively applied to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Jiaqi Li , Qianshan Wei , Chuanyi Zhang , Guilin Qi , Miaozeng Du , Yongrui Chen , Sheng Bi , Fan Liu

Machine Learning models thrive on vast datasets, continuously adapting to provide accurate predictions and recommendations. However, in an era dominated by privacy concerns, Machine Unlearning emerges as a transformative approach, enabling…

Machine Learning · Computer Science 2025-12-10 Robert Dilworth

Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Matthew Lyle Olson , Musashi Hinck , Neale Ratzlaff , Changbai Li , Phillip Howard , Vasudev Lal , Shao-Yen Tseng

Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing serious privacy risks. To mitigate this, MLLM unlearning methods are proposed, which fine-tune MLLMs to reduce…

Machine Learning · Computer Science 2025-09-23 Xianren Zhang , Hui Liu , Delvin Ce Zhang , Xianfeng Tang , Qi He , Dongwon Lee , Suhang Wang

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In real-world scenarios, model owners…

Computation and Language · Computer Science 2025-02-12 Guangyao Dou , Zheyuan Liu , Qing Lyu , Kaize Ding , Eric Wong