English
Related papers

Related papers: Quantitative Bounds for Length Generalization in T…

200 papers

Large language models (LLMs) are remarkably efficient across a wide range of natural language processing tasks and well beyond them. However, a comprehensive theoretical analysis of the LLMs' generalization capabilities remains elusive. In…

Algorithmic generalization in machine learning refers to the ability to learn the underlying algorithm that generates data in a way that generalizes out-of-distribution. This is generally considered a difficult task for most machine…

Machine Learning · Computer Science 2024-01-17 Simon Ouellette , Rolf Pfister , Hansueli Jud

This paper studies generalization error bounds for Transformer models. Based on the offset Rademacher complexity, we derive sharper generalization bounds for different Transformer architectures, including single-layer single-head,…

Machine Learning · Computer Science 2026-03-24 Yawen Li , Tao Hu , Zhouhui Lian , Wan Tian , Yijie Peng , Huiming Zhang , Zhongyi Li

Despite their recent successes, Transformer-based large language models show surprising failure modes. A well-known example of such failure modes is their inability to length-generalize: solving problem instances at inference time that are…

Computation and Language · Computer Science 2024-08-13 MohammadReza Ebrahimi , Sunny Panchal , Roland Memisevic

Large Language Models (LLMs) are pretrained on massive datasets and later instruction-tuned via supervised fine-tuning (SFT) or reinforcement learning (RL). Best practices emphasize large, diverse pretraining data, whereas post-training…

Machine Learning · Computer Science 2026-03-03 Adel Javanmard , Baharan Mirzasoleiman , Vahab Mirrokni

Grokking -- the delayed transition from memorization to generalization in small algorithmic tasks -- remains poorly understood. We present a geometric analysis of optimization dynamics in transformers trained on modular arithmetic. PCA of…

Machine Learning · Computer Science 2026-04-06 Yongzhong Xu

Transformer large language models (LLMs) have sparked admiration for their exceptional performance on tasks that demand intricate multi-step reasoning. Yet, these models simultaneously show failures on surprisingly trivial problems. This…

Most currently deployed large language models (LLMs) undergo continuous training or additional finetuning. By contrast, most research into LLMs' internal mechanisms focuses on models at one snapshot in time (the end of pre-training),…

Machine Learning · Computer Science 2024-11-27 Curt Tigges , Michael Hanna , Qinan Yu , Stella Biderman

Large language models (LLMs) are increasingly optimized for long reasoning, under the assumption that more reasoning leads to better performance. However, emerging evidence suggests that longer responses can sometimes degrade accuracy…

Computation and Language · Computer Science 2025-05-02 Jinyan Su , Jennifer Healey , Preslav Nakov , Claire Cardie

Transfer learning (TL) is a well-established machine learning technique to boost the generalization performance on a specific (target) task using information gained from a related (source) task, and it crucially depends on the ability of a…

Disordered Systems and Neural Networks · Physics 2024-07-11 Alessandro Ingrosso , Rosalba Pacelli , Pietro Rotondo , Federica Gerace

Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. Our study explores LLMs' long-context reasoning by probing their hidden representations. We find that while…

Computation and Language · Computer Science 2024-10-08 Taiming Lu , Muhan Gao , Kuai Yu , Adam Byerly , Daniel Khashabi

Transformers have shown a remarkable ability for in-context learning (ICL), making predictions based on contextual examples. However, while theoretical analyses have explored this prediction capability, the nature of the inferred context…

Machine Learning · Computer Science 2025-05-20 Fei Lu , Yue Yu

We analyze new generalization bounds for deep learning models trained by transfer learning from a source to a target task. Our bounds utilize a quantity called the majority predictor accuracy, which can be computed efficiently from data. We…

Machine Learning · Computer Science 2022-09-14 Cuong N. Nguyen , Lam Si Tung Ho , Vu Dinh , Tal Hassner , Cuong V. Nguyen

Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…

Computation and Language · Computer Science 2025-02-13 Çağatay Yıldız , Nishaanth Kanna Ravichandran , Nitin Sharma , Matthias Bethge , Beyza Ermis

The capacity of neural networks like the widely adopted transformer is known to be very high. Evidence is emerging that they learn successfully due to inductive bias in the training routine, typically a variant of gradient descent (GD). To…

Machine Learning · Computer Science 2023-03-09 William Merrill , Vivek Ramanujan , Yoav Goldberg , Roy Schwartz , Noah Smith

Why do neural networks trained with large learning rates for a longer time often lead to better generalization? In this paper, we delve into this question by examining the relation between training and testing loss in neural networks.…

Machine Learning · Computer Science 2024-01-23 Yinuo Ren , Chao Ma , Lexing Ying

In statistical learning theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. Recent work [Xu and Raginsky (2017)] has established a bound on the…

Machine Learning · Computer Science 2018-01-16 Ankit Pensia , Varun Jog , Po-Ling Loh

Symbolic regression algorithms search a space of mathematical expressions for formulas that explain given data. Transformer-based models have emerged as a promising, scalable approach shifting the expensive combinatorial search to a…

Machine Learning · Computer Science 2025-09-25 Henrik Voigt , Paul Kahlmeyer , Kai Lawonn , Michael Habeck , Joachim Giesen

Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to…

Computation and Language · Computer Science 2024-05-29 Jie Wang , Tao Ji , Yuanbin Wu , Hang Yan , Tao Gui , Qi Zhang , Xuanjing Huang , Xiaoling Wang

We study the generalization of over-parameterized deep networks (for image classification) in relation to the convex hull of their training sets. Despite their great success, generalization of deep networks is considered a mystery. These…

Machine Learning · Computer Science 2022-03-22 Roozbeh Yousefzadeh