English
Related papers

Related papers: Self-Regularization with Sparse Autoencoders for C…

200 papers

Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both Large Language Models (LLMs) and Vision Transformers (ViTs). By decomposing polysemantic…

Machine Learning · Computer Science 2026-05-11 Jakub Stępień , Marcin Mazur , Jacek Tabor , Przemysław Spurek

The advent of Large Language Models (LLMs) has revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks. Fine-tuning these models for specific domains, particularly…

Artificial Intelligence · Computer Science 2025-04-21 Chenlu Ding , Jiancan Wu , Yancheng Yuan , Jinda Lu , Kai Zhang , Alex Su , Xiang Wang , Xiangnan He

Large language models (LLMs) learn non-trivial abstractions during pretraining, such as detecting irregular plural noun subjects. However, because traditional evaluation methods (e.g., benchmarking) fail to reveal how models acquire these…

Computation and Language · Computer Science 2026-05-01 Deniz Bayazit , Aaron Mueller , Antoine Bosselut

Autoencoders have been widely used for dimensional reduction and feature extraction. Various types of autoencoders have been proposed by introducing regularization terms. Most of these regularizations improve representation learning by…

Machine Learning · Computer Science 2020-06-26 Yuzhu Guo , Kang Pan , Simeng Li , Zongchang Han , Kexin Wang , Li Li

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

This paper proposes an automatic speech recognition (ASR) model for hate speech using large language models (LLMs). The proposed method integrates the encoder of the ASR model with the decoder of the LLMs, enabling simultaneous…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-09 Ryutaro Oshima , Yuya Hosoda , Youji Iiguni

With the advancement in capabilities of Large Language Models (LLMs), one major step in the responsible and safe use of such LLMs is to be able to detect text generated by these models. While supervised AI-generated text detectors perform…

Computation and Language · Computer Science 2024-03-26 Amrita Bhattacharjee , Raha Moraffah , Joshua Garland , Huan Liu

A common goal of mechanistic interpretability is to decompose the activations of neural networks into features: interpretable properties of the input computed by the model. Sparse autoencoders (SAEs) are a popular method for finding these…

Machine Learning · Computer Science 2025-02-10 Patrick Leask , Bart Bussmann , Michael Pearce , Joseph Bloom , Curt Tigges , Noura Al Moubayed , Lee Sharkey , Neel Nanda

Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Clément Cornet , Romaric Besançon , Hervé Le Borgne

Standard statistical learning theory predicts that Large Language Models (LLMs) should overfit because their parameter counts vastly exceed the number of training tokens. Yet, in practice, they generalize robustly. We propose that the…

Machine Learning · Computer Science 2026-02-13 Dibyanayan Bandyopadhyay , Asif Ekbal

The process of tuning the size of the hidden layers for autoencoders has the benefit of providing optimally compressed representations for the input data. However, such hyper-parameter tuning process would take a lot of computation and time…

Machine Learning · Computer Science 2025-07-08 Sarthak Ketanbhai Modi , Zi Pong Lim , Yushi Cao , Yupeng Cheng , Yon Shin Teo , Shang-Wei Lin

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many…

Machine Learning · Computer Science 2025-11-06 Xiaoqing Sun , Alessandro Stolfo , Joshua Engels , Ben Wu , Senthooran Rajamanoharan , Mrinmaya Sachan , Max Tegmark

Autoencoders (AE) are simple yet powerful class of neural networks that compress data by projecting input into low-dimensional latent space (LS). Whereas LS is formed according to the loss function minimization during training, its…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Nikita Gabdullin

Semi-Supervised Variational Autoencoders (SSVAEs) are widely used models for data efficient learning. In this paper, we question the adequacy of the standard design of sequence SSVAEs for the task of text classification as we exhibit two…

Computation and Language · Computer Science 2021-09-28 Ghazi Felhi , Joseph Le Roux , Djamé Seddah

A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language…

Machine Learning · Computer Science 2024-11-08 Jacob Dunefsky , Philippe Chlenski , Neel Nanda

Going beyond mimicking limited human experiences, recent studies show initial evidence that, like humans, large language models (LLMs) are capable of improving their abilities purely by self-correction, i.e., correcting previous responses…

Machine Learning · Computer Science 2024-11-19 Yifei Wang , Yuyang Wu , Zeming Wei , Stefanie Jegelka , Yisen Wang

Autoencoders and their variations provide unsupervised models for learning low-dimensional representations for downstream tasks. Without proper regularization, autoencoder models are susceptible to the overfitting problem and the so-called…

Machine Learning · Computer Science 2020-01-23 Hanwei Wu , Markus Flierl

Machine learning and especially deep learning have garneredtremendous popularity in recent years due to their increased performanceover other methods. The availability of large amount of data has aidedin the progress of deep learning.…

Machine Learning · Computer Science 2019-09-06 Sharath M. Shankaranarayana , Davor Runje

Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation.…

Computation and Language · Computer Science 2023-09-26 Yuxuan Liu , Tianchi Yang , Shaohan Huang , Zihan Zhang , Haizhen Huang , Furu Wei , Weiwei Deng , Feng Sun , Qi Zhang

Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human ability to understand them, however, remain very limited. This is especially…

Machine Learning · Computer Science 2018-12-27 Babajide O. Ayinde , Jacek M. Zurada