English
Related papers

Related papers: Self-Ablating Transformers: More Interpretability,…

200 papers

We introduce Sparse Concept Anchoring, a method that biases latent space to position a targeted subset of concepts while allowing others to self-organize, using only minimal supervision (labels for <0.1% of examples per anchored concept).…

Machine Learning · Computer Science 2026-04-28 Sandy Fraser , Patryk Wielopolski

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

An approach to improve network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We find pretrained models to be highly unclusterable and thus train models to be more…

Machine Learning · Computer Science 2025-07-29 Satvik Golechha , Dylan Cope , Nandi Schoots

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…

Computer Vision and Pattern Recognition · Computer Science 2024-08-09 Hefeng Wu , Hao Jiang , Keze Wang , Ziyi Tang , Xianghuan He , Liang Lin

Hallucinations in large language models are a widespread problem, yet the mechanisms behind whether models will hallucinate are poorly understood, limiting our ability to solve this problem. Using sparse autoencoders as an interpretability…

Computation and Language · Computer Science 2025-02-11 Javier Ferrando , Oscar Obeso , Senthooran Rajamanoharan , Neel Nanda

Neural networks are growing more capable on their own, but we do not understand their neural mechanisms. Understanding these mechanisms' decision-making processes, or mechanistic interpretability, enables (1) accountability and control in…

Computation and Language · Computer Science 2026-03-02 Mason Kadem , Rong Zheng

While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging models to hallucinate,…

Computation and Language · Computer Science 2022-12-21 David Dale , Elena Voita , Loïc Barrault , Marta R. Costa-jussà

We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large language models. The system runs two coupled loops: (1) explanation refinement, where an…

Computation and Language · Computer Science 2026-05-05 Arnau Marin-Llobet , Javier Ferrando

Sparsity is regarded as a desirable property of representations, especially in terms of explanation. However, its usage has been limited due to the gap with dense representations. Most NLP research progresses in recent years are based on…

Computation and Language · Computer Science 2019-11-11 Wenpeng Hu , Mengyu Wang , Bing Liu , Feng Ji , Haiqing Chen , Dongyan Zhao , Jinwen Ma , Rui Yan

Sparse connectivity is a hallmark of the brain and a desired property of artificial neural networks. It promotes energy efficiency, simplifies training, and enhances the robustness of network function. Thus, a detailed understanding of how…

Disordered Systems and Neural Networks · Physics 2024-09-10 Mirza M. Junaid Baig , Armen Stepanyants

Transformer language models are state of the art in a multitude of NLP tasks. Despite these successes, their opaqueness remains problematic. Recent methods aiming to provide interpretability and explainability to black-box models primarily…

Computation and Language · Computer Science 2022-03-14 Felix Friedrich , Patrick Schramowski , Christopher Tauchmann , Kristian Kersting

Many applications in signal processing benefit from the sparsity of signals in a certain transform domain or dictionary. Synthesis sparsifying dictionaries that are directly adapted to data have been popular in applications such as image…

Machine Learning · Statistics 2015-06-23 Saiprasad Ravishankar , Yoram Bresler

Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding…

Computation and Language · Computer Science 2016-10-14 Yunchuan Chen , Lili Mou , Yan Xu , Ge Li , Zhi Jin

Real-world processes often contain intermediate state that can be modeled as an extremely sparse activation tensor. In this work, we analyze the identifiability of such sparse and local latent intermediate variables, which we call motifs.…

Machine Learning · Computer Science 2026-03-04 Kavi Gupta , Osbert Bastani , Armando Solar-Lezama

Large pre-trained transformers are show-stealer in modern-day deep learning, and it becomes crucial to comprehend the parsimonious patterns that exist within them as they grow in scale. With exploding parameter counts, Lottery Ticket…

Machine Learning · Computer Science 2023-08-11 Ajay Jaiswal , Shiwei Liu , Tianlong Chen , Zhangyang Wang

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

Computation and Language · Computer Science 2022-10-03 Chendong Zhao , Jianzong Wang , Wen qi Wei , Xiaoyang Qu , Haoqian Wang , Jing Xiao

It has been long known that sparsity is an effective inductive bias for learning efficient representation of data in vectors with fixed dimensionality, and it has been explored in many areas of representation learning. Of particular…

Computation and Language · Computer Science 2021-04-20 Victor Prokhorov , Yingzhen Li , Ehsan Shareghi , Nigel Collier

Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical analysis of the…

Machine Learning · Computer Science 2022-06-27 Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Cyril Zhang

We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations. Concretely, we introduce a meta sorting network that learns to…

Machine Learning · Computer Science 2020-02-27 Yi Tay , Dara Bahri , Liu Yang , Donald Metzler , Da-Cheng Juan

The attention mechanism in its standard implementation contains extraneous rotational degrees of freedom that are carried through computation but do not affect model activations or outputs. We introduce a simple symmetry-breaking protocol…

Machine Learning · Computer Science 2026-02-13 Eva Silverstein , Daniel Kunin , Vasudev Shyam
‹ Prev 1 3 4 5 6 7 10 Next ›