English
Related papers

Related papers: Hidden Breakthroughs in Language Model Training

200 papers

Large language models (LLMs) can perform remarkably complex tasks, yet the fine-grained details of how these capabilities emerge during pretraining remain poorly understood. Scaling laws on validation loss tell us how much a model improves…

Computation and Language · Computer Science 2026-04-10 Emmy Liu , Kaiser Sun , Millicent Li , Isabelle Lee , Lindia Tjuatja , Jen-tse Huang , Graham Neubig

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Artificial Intelligence · Computer Science 2026-01-06 Josef Ott

Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts observations. Due to such events'…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Fabio Valerio Massoli , Fabrizio Falchi , Alperen Kantarci , Şeymanur Akti , Hazim Kemal Ekenel , Giuseppe Amato

Large language models (LLMs) often exhibit abrupt emergent behavior, whereby new abilities arise at certain points during their training. This phenomenon, commonly referred to as a ''phase transition'', remains poorly understood. In this…

Computation and Language · Computer Science 2025-04-01 Yuko Nakagi , Keigo Tada , Sota Yoshino , Shinji Nishimoto , Yu Takagi

Many self-supervised speech models, varying in their pre-training objective, input modality, and pre-training data, have been proposed in the last few years. Despite impressive successes on downstream tasks, we still have a limited…

Computation and Language · Computer Science 2023-03-20 Ankita Pasad , Bowen Shi , Karen Livescu

Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representations with language-specific decoding, and if so, why does…

Computation and Language · Computer Science 2026-02-10 Abir Harrasse , Florent Draye , Punya Syon Pandey , Zhijing Jin , Bernhard Schölkopf

We present observations and discussion of previously unreported phenomena discovered while training residual networks. The goal of this work is to better understand the nature of neural networks through the examination of these new…

Machine Learning · Computer Science 2017-02-15 Leslie N. Smith , Nicholay Topin

We propose LoRA-MCL, a training scheme that extends next-token prediction in language models with a method designed to decode diverse, plausible sentence continuations at inference time. Traditional language modeling is an intrinsically…

Machine Learning · Computer Science 2026-02-05 Victor Letzelter , Hugo Malard , Mathieu Fontaine , Gaël Richard , Slim Essid , Andrei Bursuc , Patrick Pérez

How do language models learn to make predictions during pre-training? To study this, we extract learning curves from five autoregressive English language model pre-training runs, for 1M unseen tokens in context. We observe that the language…

Computation and Language · Computer Science 2024-08-01 Tyler A. Chang , Zhuowen Tu , Benjamin K. Bergen

We investigate the training dynamics of deep classifiers by examining how hierarchical relationships between classes evolve during training. Through extensive experiments, we argue that the learning process in classification problems can be…

Artificial Intelligence · Computer Science 2025-02-18 Roman Malashin , Valeria Yachnaya , Alexander Mullin

Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger…

Machine Learning · Computer Science 2025-02-20 Yifei Yang , Zouying Cao , Xinbei Ma , Yao Yao , Libo Qin , Zhi Chen , Hai Zhao

Machine learning has been successfully used to study phase transitions. One of the most popular approaches to identifying critical points from data without prior knowledge of the underlying phases is the learning-by-confusion scheme. As…

Machine Learning · Computer Science 2023-11-16 Julian Arnold , Frank Schäfer , Niels Lörch

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

Computation and Language · Computer Science 2025-01-31 Didier Chételat , Joseph Cotnareanu , Rylee Thompson , Yingxue Zhang , Mark Coates

Unsupervised learning aims at the discovery of hidden structure that drives the observations in the real world. It is essential for success in modern machine learning. Latent variable models are versatile in unsupervised learning and have…

Machine Learning · Computer Science 2016-06-13 Furong Huang

Machine learning models in dynamic environments often suffer from concept drift, where changes in the data distribution degrade performance. While detecting this drift is a well-studied topic, explaining how and why the model's…

Machine Learning · Computer Science 2025-09-12 Ignacy Stępka , Jerzy Stefanowski

Continual Learning (CL) aims to enable models to continuously acquire new knowledge from a sequence of tasks with avoiding the forgetting of learned information. However, existing CL methods only rely on the parameters of the most recent…

Machine Learning · Computer Science 2025-10-24 Haomiao Qiu , Miao Zhang , Ziyue Qiao , Liqiang Nie

We explore the topology of representation manifolds arising in autoregressive neural language models trained on raw text data. In order to study their properties, we introduce tools from computational algebraic topology, which we use as a…

Computation and Language · Computer Science 2024-06-11 Stephen Fitz , Peter Romero , Jiyan Jonas Schneider

Large language models have led to significant progress across many NLP tasks, although their massive sizes often incur substantial computational costs. Distillation has become a common practice to compress these large and highly capable…

Computation and Language · Computer Science 2026-01-06 Zishun Yu , Shangzhe Li , Xinhua Zhang

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

Machine Learning · Computer Science 2026-05-20 Zhipeng Zhang

Large pretrained language models have been performing increasingly well in a variety of downstream tasks via prompting. However, it remains unclear from where the model learns the task-specific knowledge, especially in a zero-shot setup. In…

Computation and Language · Computer Science 2022-05-26 Xiaochuang Han , Yulia Tsvetkov
‹ Prev 1 3 4 5 6 7 10 Next ›