English
Related papers

Related papers: Learning Sparse Sentence Encoding without Supervis…

200 papers

We study the challenge of achieving theoretically grounded feature recovery using Sparse Autoencoders (SAEs) for the interpretation of Large Language Models. Existing SAE training algorithms often lack rigorous mathematical guarantees and…

Machine Learning · Computer Science 2025-06-18 Siyu Chen , Heejune Sheen , Xuyuan Xiong , Tianhao Wang , Zhuoran Yang

Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…

Computation and Language · Computer Science 2024-02-14 Chenghao Xiao , Zhuoxu Huang , Danlu Chen , G Thomas Hudson , Yizhi Li , Haoran Duan , Chenghua Lin , Jie Fu , Jungong Han , Noura Al Moubayed

Learning from heterogeneous data poses challenges such as combining data from various sources and of different types. Meanwhile, heterogeneous data are often associated with missingness in real-world applications due to heterogeneity and…

Machine Learning · Computer Science 2021-02-26 Yu Gong , Hossein Hajimirsadeghi , Jiawei He , Thibaut Durand , Greg Mori

Fair and unbiased machine learning is an important and active field of research, as decision processes are increasingly driven by models that learn from data. Unfortunately, any biases present in the data may be learned by the model,…

Machine Learning · Computer Science 2020-02-27 Matthew J. Vowels , Necati Cihan Camgoz , Richard Bowden

Despite the excellent performance of vision-language pre-trained models (VLPs) on conventional VQA task, they still suffer from two problems: First, VLPs tend to rely on language biases in datasets and fail to generalize to…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 Qingyi Si , Yuanxin Liu , Zheng Lin , Peng Fu , Weiping Wang

Learning interpretable and disentangled representations of data is a key topic in machine learning research. Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. It employs a clear…

Machine Learning · Computer Science 2020-06-04 Andriy Serdega , Dae-Shik Kim

Several approximate inference methods have been proposed for deep discrete latent variable models. However, non-parametric methods which have previously been successfully employed for classical sparse coding models have largely been…

Machine Learning · Computer Science 2023-03-16 Arunesh Mittal , Kai Yang , Paul Sajda , John Paisley

Variational auto-encoders (VAEs) are a powerful approach to unsupervised learning. They enable scalable approximate posterior inference in latent-variable models using variational inference (VI). A VAE posits a variational family…

Machine Learning · Computer Science 2022-06-08 Samarth Sinha , Adji B. Dieng

Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit severe accuracy degradation at high sparsity. We show that this…

Machine Learning · Computer Science 2026-05-22 Haotian Xu , Jiannan Yang , Tian Gao , Tsui-Wei Weng , Tengfei Ma

Current distributed representations of words show little resemblance to theories of lexical semantics. The former are dense and uninterpretable, the latter largely based on familiar, discrete classes (e.g., supersenses) and relations (e.g.,…

Computation and Language · Computer Science 2015-06-08 Manaal Faruqui , Yulia Tsvetkov , Dani Yogatama , Chris Dyer , Noah Smith

Sparse autoencoders (SAEs) are a popular tool for interpreting large language model activations, but their utility in addressing open questions in interpretability remains unclear. In this work, we demonstrate their effectiveness by using…

Machine Learning · Computer Science 2025-04-21 Dmitrii Kharlapenko , Stepan Shabalin , Fazl Barez , Arthur Conmy , Neel Nanda

A fundamental problem faced by object recognition systems is that objects and their features can appear in different locations, scales and orientations. Current deep learning methods attempt to achieve invariance to local translations via…

Computer Vision and Pattern Recognition · Computer Science 2017-12-12 Dimitrios C. Gklezakos , Rajesh P. N. Rao

Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs). However, they typically rely on autoencoders constrained by some training-time regularization on…

Machine Learning · Computer Science 2026-02-13 Hakaze Cho , Haolin Yang , Yanshu Li , Brian M. Kurkoski , Naoya Inoue

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Information Retrieval · Computer Science 2026-02-18 Anton Klenitskiy , Konstantin Polev , Daria Denisova , Alexey Vasilev , Dmitry Simakov , Gleb Gusev

In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this…

Machine Learning · Computer Science 2025-12-10 Shiqi Liu , Jingxin Liu , Qian Zhao , Xiangyong Cao , Huibin Li , Deyu Meng , Hongying Meng , Sheng Liu

An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as…

Computation and Language · Computer Science 2017-09-25 Wei-Ning Hsu , Yu Zhang , James Glass

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Computation and Language · Computer Science 2025-02-27 Sumanta Bhattacharyya , Pedram Rooshenas

Linking neural representations to linguistic factors is crucial in order to build and analyze NLP models interpretable by humans. Among these factors, syntactic roles (e.g. subjects, direct objects,$\dots$) and their realizations are…

Computation and Language · Computer Science 2022-06-23 Ghazi Felhi , Joseph Le Roux , Djamé Seddah

Sparse coding has been incorporated in models of the visual cortex for its computational advantages and connection to biology. But how the level of sparsity contributes to performance on visual tasks is not well understood. In this work,…

Computer Vision and Pattern Recognition · Computer Science 2022-01-19 Joshua Bowren , Luis Sanchez-Giraldo , Odelia Schwartz

We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fixed-dimensional Euclidean representations. We formalize the functional representation hypothesis,…

Machine Learning · Computer Science 2026-05-11 Bahareh Tolooshams , Ailsa Shen , Anima Anandkumar