English
Related papers

Related papers: Rethinking the Outlier Distribution in Large Langu…

200 papers

Outliers introduce significant training challenges in neural networks by propagating erroneous gradients, which can degrade model performance and generalization. We propose the Z-Error Loss, a statistically principled approach that…

Machine Learning · Computer Science 2025-06-04 Guillaume Godin

Transformer-based large language models (LLMs) have achieved great success with the growing model size. LLMs' size grows by $240\times$ every two years, which outpaces the hardware progress and makes model inference increasingly costly.…

Hardware Architecture · Computer Science 2023-04-18 Cong Guo , Jiaming Tang , Weiming Hu , Jingwen Leng , Chen Zhang , Fan Yang , Yunxin Liu , Minyi Guo , Yuhao Zhu

We identify a new phenomenon in neural network optimization which arises from the interaction of depth and a particular heavy-tailed structure in natural data. Our result offers intuitive explanations for several previously reported…

Machine Learning · Computer Science 2023-11-08 Elan Rosenfeld , Andrej Risteski

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for simple, surface-level textual relations over full semantic complexity of the problem. This proposal investigates a…

Computation and Language · Computer Science 2022-06-20 Michal Štefánik

The quantization of large language models (LLMs) has been a prominent research area aimed at enabling their lightweight deployment in practice. Existing research about LLM's quantization has mainly explored the interplay between weights and…

Computation and Language · Computer Science 2025-05-16 Yifei Gao , Jie Ou , Lei Wang , Jun Cheng , Mengchu Zhou

Large Language Models (LLMs) have advanced rapidly but face significant memory demands. While quantization has shown promise for LLMs, current methods typically require lengthy training to alleviate the performance degradation from…

Artificial Intelligence · Computer Science 2024-05-31 Ke Yi , Yuhui Xu , Heng Chang , Chen Tang , Yuan Meng , Tong Zhang , Jia Li

Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance. Previous works have argued that although ablating these outlier dimensions in LLM representations…

Computation and Language · Computer Science 2024-01-24 William Rudman , Catherine Chen , Carsten Eickhoff

To overcome the burden on the memory size and bandwidth due to ever-increasing size of large language models (LLMs), aggressive weight quantization has been recently studied, while lacking research on quantizing activations. In this paper,…

Machine Learning · Computer Science 2024-09-25 Jahyun Koo , Dahoon Park , Sangwoo Jung , Jaeha Kung

Dynamic factor models have a wide range of applications in econometrics and applied economics. The basic motivation resides in their capability of reducing a large set of time series to only few indicators (factors). If the number of time…

Statistics Theory · Mathematics 2009-09-29 Roberto Baragona , Francesco Battaglia

We investigate the origins of massive activations in large language models (LLMs) and identify a specific layer named the \textbf{Massive Emergence Layer (ME Layer)}, that is consistently observed across model families, where massive…

Computation and Language · Computer Science 2026-05-14 Zeru Shi , Zhenting Wang , Fan Yang , Qifan Wang , Ruixiang Tang

While Transformer-based language models are generally very robust to pruning, there is the recently discovered outlier phenomenon: disabling only 48 out of 110M parameters in BERT-base drops its performance by nearly 30% on MNLI. We…

Computation and Language · Computer Science 2024-06-19 Giovanni Puccetti , Anna Rogers , Aleksandr Drozd , Felice Dell'Orletta

This study explores the impact of class outliers on the effectiveness of example-based explainability methods for black-box machine learning models. We reformulate existing explainability evaluation metrics, such as correctness and…

Machine Learning · Computer Science 2024-08-02 Ikhtiyor Nematov , Dimitris Sacharidis , Tomer Sagi , Katja Hose

Outlier detection algorithms typically assign an outlier score to each observation in a dataset, indicating the degree to which an observation is an outlier. However, these scores are often not comparable across algorithms and can be…

Machine Learning · Computer Science 2024-10-31 Philipp Röchner , Henrique O. Marques , Ricardo J. G. B. Campello , Arthur Zimek , Franz Rothlauf

In recent years the machine learning techniques have shown a great potential in various problems from a multitude of disciplines, including materials design and drug discovery. The high computational speed on the one hand and the accuracy…

Chemical Physics · Physics 2018-05-09 Konstantin Gubaev , Evgeny V. Podryabinkin , Alexander V. Shapeev

In real world, our datasets often contain outliers. Moreover, the outliers can seriously affect the final machine learning result. Most existing algorithms for handling outliers take high time complexities (e.g. quadratic or cubic…

Computational Geometry · Computer Science 2020-02-28 Hu Ding , Zixiu Wang

Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks, but they are hindered by high computational costs and memory requirements. Ternarization, an extreme form of quantization, offers…

Machine Learning · Computer Science 2024-06-12 Tianqi Chen , Zhe Li , Weixiang Xu , Zeyu Zhu , Dong Li , Lu Tian , Emad Barsoum , Peisong Wang , Jian Cheng

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to…

Computation and Language · Computer Science 2025-11-20 Moses Kiprono

LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risks: an adversary may release a model that appears benign in full precision but exhibits…

Machine Learning · Computer Science 2026-05-15 Xiaohua Zhan , Kazuki Egashira , Robin Staab , Mark Vero , Martin Vechev

Outliers are ubiquitous in modern data sets. Distance-based techniques are a popular non-parametric approach to outlier detection as they require no prior assumptions on the data generating distribution and are simple to implement. Scaling…

Machine Learning · Statistics 2016-05-04 Mario Lucic , Olivier Bachem , Andreas Krause

In recent years, active learning has been successfully applied to an array of NLP tasks. However, prior work often assumes that training and test data are drawn from the same distribution. This is problematic, as in real-life settings data…

Computation and Language · Computer Science 2023-02-15 Ard Snijders , Douwe Kiela , Katerina Margatina