English
Related papers

Related papers: Neurons in Large Language Models: Dead, N-gram, Po…

200 papers

We present a new family of exchangeable stochastic processes, the Functional Neural Processes (FNPs). FNPs model distributions over functions by learning a graph of dependencies on top of latent representations of the points in the given…

Machine Learning · Computer Science 2019-11-05 Christos Louizos , Xiahan Shi , Klamer Schutte , Max Welling

As large language models (LLMs) scale, the question is not only how large they become, but how much of their capacity is effectively utilized. Existing scaling laws relate model size to loss, yet overlook how components exploit their latent…

Machine Learning · Computer Science 2025-10-02 Nandan Kumar Jha , Brandon Reagen

Graph neural networks (GNNs) are the de facto standard deep learning architectures for machine learning on graphs. This has led to a large body of work analyzing the capabilities and limitations of these models, particularly pertaining to…

Machine Learning · Computer Science 2024-11-11 Sam Adam-Day , Theodor Mihai Iliant , İsmail İlkan Ceylan

The need for more transparency of the decision-making processes in artificial neural networks steadily increases driven by their applications in safety critical and ethically challenging domains such as autonomous driving or medical…

Neural and Evolutionary Computing · Computer Science 2020-05-12 Richard Meyes , Constantin Waubert de Puiseau , Andres Posada-Moreno , Tobias Meisen

Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data. However, typical fine-tuning schemes do not prioritize the examples that they tune on. We show that, if you can prioritize…

Computation and Language · Computer Science 2023-05-12 Ian Osband , Seyed Mohammad Asghari , Benjamin Van Roy , Nat McAleese , John Aslanides , Geoffrey Irving

We refer to a machine learning situation where models based on classical convolutional neural networks have shown good performance. We are investigating different encoding techniques in the form of supervoxels, then graphs to reduce the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Lukman Ismaila , Pejman Rasti , Jean-Michel Lemée , David Rousseau

A long-running goal of the clinical NLP community is the extraction of important variables trapped in clinical notes. However, roadblocks have included dataset shift from the general domain and a lack of public clinical corpora and…

Computation and Language · Computer Science 2022-12-01 Monica Agrawal , Stefan Hegselmann , Hunter Lang , Yoon Kim , David Sontag

Recent studies have shown that deep neural networks (DNNs) perform significantly better than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech recognition tasks. In this paper, we argue that the improved…

Machine Learning · Computer Science 2018-12-06 Dong Yu , Michael L. Seltzer , Jinyu Li , Jui-Ting Huang , Frank Seide

Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multilingual content into English-aligned representations at…

Computation and Language · Computer Science 2026-01-30 Chengzhi Zhong , Fei Cheng , Qianying Liu , Yugo Murawaki , Chenhui Chu , Sadao Kurohashi

Word segmentation is the task of inserting or deleting word boundary characters in order to separate character sequences that correspond to words in some language. In this article we propose an approach based on a beam search algorithm and…

Computation and Language · Computer Science 2018-12-04 Yerai Doval , Carlos Gómez-Rodríguez

Recent advancements in language representation models such as BERT have led to a rapid improvement in numerous natural language processing tasks. However, language models usually consist of a few hundred million trainable parameters with…

Machine Learning · Computer Science 2019-12-12 Mehrdad Valipour , En-Shiun Annie Lee , Jaime R. Jamacaro , Carolina Bessega

Linear layers in neural networks (NNs) trained by gradient descent can be expressed as a key-value memory system which stores all training datapoints and the initial weights, and produces outputs using unnormalised dot attention over the…

Machine Learning · Computer Science 2022-06-20 Kazuki Irie , Róbert Csordás , Jürgen Schmidhuber

Recently, text classification model based on graph neural network (GNN) has attracted more and more attention. Most of these models adopt a similar network paradigm, that is, using pre-training node embedding initialization and two-layer…

Computation and Language · Computer Science 2023-01-26 Jiayuan Chen , Boyu Zhang , Yinfei Xu , Meng Wang

Large, pretrained language models infer powerful representations that encode rich semantic and syntactic content, albeit implicitly. In this work we introduce a novel neural language model that enforces, via inductive biases, explicit…

Computation and Language · Computer Science 2023-05-29 Ramsés J. Sánchez , Lukas Conrads , Pascal Welke , Kostadin Cvejoski , César Ojeda

Networks are abundant in biological systems. Small sized over-represented network motifs have been discovered, and it has been suggested that these constitute functional building blocks. We ask whether larger dynamical network motifs exist…

Neural and Evolutionary Computing · Computer Science 2018-09-25 C. H. Huck Yang , Rise Ooi , Tom Hiscock , Victor Eguiluz , Jesper Tegnér

Interpretability researchers have attempted to understand MLP neurons of language models based on both the contexts in which they activate and their output weight vectors. They have paid little attention to a complementary aspect: the…

Machine Learning · Computer Science 2025-05-26 Sebastian Gerstner , Hinrich Schütze

Prior work has shown the existence of contextual neurons in language models, including a neuron that activates on German text. We show that this neuron exists within a broader contextual n-gram circuit: we find late layer neurons which…

Machine Learning · Computer Science 2023-11-03 Lucia Quirke , Lovis Heindrich , Wes Gurnee , Neel Nanda

The emergence of discourse-like tokens such as "wait" and "therefore" in large language models (LLMs) has offered a unique window into their reasoning processes. However, systematic analyses of how such signals vary across training…

Computation and Language · Computer Science 2026-01-27 Jaehui Hwang , Dongyoon Han , Sangdoo Yun , Byeongho Heo

We show that MLP layers in transformer language models perform binary routing of continuous signals: the decision of whether a token needs nonlinear processing is well-captured by binary neuron activations, even though the signals being…

Machine Learning · Computer Science 2026-03-12 Peter Balogh

In this work we determine a process-level Large Deviation Principle (LDP) for a model of interacting neurons indexed by a lattice $\mathbb{Z}^d$. The neurons are subject to noise, which is modelled as a correlated martingale. The…

Probability · Mathematics 2016-04-05 Olivier Faugeras , James MacLaurin
‹ Prev 1 4 5 6 7 8 10 Next ›