English
Related papers

Related papers: Linear Representation Transferability Hypothesis: …

200 papers

Language models increasingly appear to learn similar representations, despite differences in training objectives, architectures, and data modalities. This emerging compatibility between independently trained models introduces new…

Artificial Intelligence · Computer Science 2026-05-26 Matt Gorbett , Suman Jana

In this work, we demonstrate that affine mappings between residual streams of language models is a cheap way to effectively transfer represented features between models. We apply this technique to transfer the weights of Sparse Autoencoders…

Computation and Language · Computer Science 2025-11-04 Alan Chen , Jack Merullo , Alessandro Stolfo , Ellie Pavlick

Deep neural networks trained on a wide range of datasets demonstrate impressive transferability. Deep features appear general in that they are applicable to many datasets and tasks. Such property is in prevalent use in real-world…

Machine Learning · Computer Science 2019-09-27 Hong Liu , Mingsheng Long , Jianmin Wang , Michael I. Jordan

Deep neural networks come in many sizes and architectures. The choice of architecture, in conjunction with the dataset and learning algorithm, is commonly understood to affect the learned neural representations. Yet, recent results have…

Machine Learning · Computer Science 2024-07-08 Loek van Rossem , Andrew M. Saxe

Understanding the inner workings of Large Language Models (LLMs) is a critical research frontier. Prior research has shown that a single LLM's concept representations can be captured as steering vectors (SVs), enabling the control of LLM…

Computation and Language · Computer Science 2025-05-21 Youcheng Huang , Chen Huang , Duanyu Feng , Wenqiang Lei , Jiancheng Lv

Transformer models bring propelling advances in various NLP tasks, thus inducing lots of interpretability research on the learned representations of the models. However, we raise a fundamental question regarding the reliability of the…

Computation and Language · Computer Science 2023-05-25 Yuxin Ren , Qipeng Guo , Zhijing Jin , Shauli Ravfogel , Mrinmaya Sachan , Bernhard Schölkopf , Ryan Cotterell

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

Machine Learning · Computer Science 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

The internal representations learned by deep networks are often sensitive to architecture-specific choices, raising questions about the stability, alignment, and transferability of learned structure across models. In this paper, we…

Machine Learning · Computer Science 2025-08-06 Saleh Nikooroo , Thomas Engel

Foundation models learn highly transferable representations through large-scale pretraining on diverse data. An increasing body of research indicates that these representations exhibit a remarkable degree of similarity across architectures…

Artificial Intelligence · Computer Science 2025-10-08 Jianglin Lu , Hailing Wang , Yi Xu , Yizhou Wang , Kuo Yang , Yun Fu

Deep Reinforcement Learning (RL) has demonstrated success in solving complex sequential decision-making problems by integrating neural networks with the RL framework. However, training deep RL models poses several challenges, such as the…

Machine Learning · Computer Science 2025-09-30 Sooraj Sathish , Keshav Goyal , Raghuram Bharadwaj Diddigi

We consider Representation Misdirection (RM), a class of large language model (LLM) unlearning methods that achieve forgetting by redirecting the forget-representations, that is, latent representations of forget-samples, toward a target…

Machine Learning · Computer Science 2026-05-18 Tien Dang , The-Hai Nguyen , Dinh Mai Phuong , Nguyen Minh Phuong , Anh Bui , Hoang Thanh-Tung , Le-Minh Nguyen , Naoya Inoue

As NNs permeate various scientific and industrial domains, understanding the universality and reusability of their representations becomes crucial. At their core, these networks create intermediate neural representations, indicated as…

Machine Learning · Computer Science 2024-06-18 Luca Moschella

The Linear Representation Hypothesis (LRH) states that neural networks learn to encode concepts as directions in activation space, and a strong version of the LRH states that models learn only such encodings. In this paper, we present a…

Machine Learning · Computer Science 2024-08-21 Róbert Csordás , Christopher Potts , Christopher D. Manning , Atticus Geiger

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

We propose the Lattice Representation Hypothesis of large language models: a symbolic backbone that grounds conceptual hierarchies and logical operations in embedding geometry. Our framework unifies the Linear Representation Hypothesis with…

Artificial Intelligence · Computer Science 2026-05-19 Bo Xiong

Large Language Models (LLMs) are pretrained on massive datasets and later instruction-tuned via supervised fine-tuning (SFT) or reinforcement learning (RL). Best practices emphasize large, diverse pretraining data, whereas post-training…

Machine Learning · Computer Science 2026-03-03 Adel Javanmard , Baharan Mirzasoleiman , Vahab Mirrokni

It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory and systematic approach quantitatively characterizing what…

Machine Learning · Computer Science 2018-11-30 Liwei Wang , Lunjia Hu , Jiayuan Gu , Yue Wu , Zhiqiang Hu , Kun He , John Hopcroft

Understanding what information neural networks capture is an essential problem in deep learning, and studying whether different models capture similar features is an initial step to achieve this goal. Previous works sought to define metrics…

Machine Learning · Computer Science 2020-07-27 Yunzhen Feng , Runtian Zhai , Di He , Liwei Wang , Bin Dong

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

Machine Learning · Computer Science 2026-02-04 Magamed Taimeskhanov , Samuel Vaiter , Damien Garreau

Representations of the world environment play a crucial role in artificial intelligence. It is often inefficient to conduct reasoning and inference directly in the space of raw sensory representations, such as pixel values of images.…

Machine Learning · Computer Science 2022-04-12 Kenji Kawaguchi , Linjun Zhang , Zhun Deng
‹ Prev 1 2 3 10 Next ›