English
Related papers

Related papers: Memorisation versus Generalisation in Pre-trained …

200 papers

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance gain comes from. In this work, we propose to answer this…

Computation and Language · Computer Science 2022-04-19 Hanjie Chen , Guoqing Zheng , Ahmed Hassan Awadallah , Yangfeng Ji

Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, such as language modelling, this can become a performance…

Machine Learning · Computer Science 2018-03-28 Jack W Rae , Chris Dyer , Peter Dayan , Timothy P Lillicrap

Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution. Continual learning could be achieved via replay -- by concurrently training externally…

Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing…

Machine Learning · Computer Science 2020-09-24 Wentao Wang , Guowei Xu , Wenbiao Ding , Gale Yan Huang , Guoliang Li , Jiliang Tang , Zitao Liu

Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perform phoneme or word-level speech recognition without labeled…

Computation and Language · Computer Science 2025-01-14 Haoyu Wang , Wei-Qiang Zhang , Hongbin Suo , Yulong Wan

Noisy labels are very common in deep supervised learning. Although many studies tend to improve the robustness of deep training for noisy labels, rare works focus on theoretically explaining the training behaviors of learning with noisily…

Machine Learning · Computer Science 2021-04-12 Yi Xu , Qi Qian , Hao Li , Rong Jin

Visual sentiment analysis has received increasing attention in recent years. However, the dataset's quality is a concern because the sentiment labels are crowd-sourcing, subjective, and prone to mistakes, and poses a severe threat to the…

Computer Vision and Pattern Recognition · Computer Science 2022-01-28 Wei Zhu , Zihe Zheng , Haitian Zheng , Hanjia Lyu , Jiebo Luo

Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has…

Computation and Language · Computer Science 2022-02-09 Junnan Liu , Qianren Mao , Bang Liu , Hao Peng , Hongdong Zhu , Jianxin Li

Large language models (LLMs) can struggle to memorize factual knowledge in their parameters, often leading to hallucinations and poor performance on knowledge-intensive tasks. In this paper, we formalize fact memorization from an…

Computation and Language · Computer Science 2026-04-10 Jiayuan Ye , Vitaly Feldman , Kunal Talwar

Despite deep learning has achieved great success, it often relies on a large amount of training data with accurate labels, which are expensive and time-consuming to collect. A prominent direction to reduce the cost is to learn with noisy…

Machine Learning · Computer Science 2024-01-31 Chuanyang Hu , Shipeng Yan , Zhitong Gao , Xuming He

Human memory is fleeting. As words are processed, the exact wordforms that make up incoming sentences are rapidly lost. Cognitive scientists have long believed that this limitation of memory may, paradoxically, help in learning language -…

Computation and Language · Computer Science 2026-05-11 Abishek Thamma , Micha Heilbron

Neural language models are usually trained to match the distributional properties of a large-scale corpus by minimizing the log loss. While straightforward to optimize, this approach forces the model to reproduce all variations in the…

Computation and Language · Computer Science 2020-05-04 Daniel Kang , Tatsunori Hashimoto

Diffusion models generalize well in practice. However, an optimal diffusion model fully memorizes the training data and therefore fails to generalize, raising the question of what induces generalization in a real diffusion model. We show…

Machine Learning · Computer Science 2026-05-21 Tim Kaiser , Markus Kollmann

We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest…

Computation and Language · Computer Science 2021-09-13 Yu Meng , Yunyi Zhang , Jiaxin Huang , Xuan Wang , Yu Zhang , Heng Ji , Jiawei Han

Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such noisy data, several algorithms have been proposed. A…

Machine Learning · Computer Science 2022-12-06 Deep Patel , P. S. Sastry

Noisy labels are ubiquitous in real-world datasets, especially in the large-scale ones derived from crowdsourcing and web searching. It is challenging to train deep neural networks with noisy datasets since the networks are prone to…

Computer Vision and Pattern Recognition · Computer Science 2024-06-26 Yangdi Lu , Wenbo He

The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well, despite being able to perfectly fit (memorise) completely random labels. To…

Machine Learning · Computer Science 2023-10-10 Michal Lukasik , Vaishnavh Nagarajan , Ankit Singh Rawat , Aditya Krishna Menon , Sanjiv Kumar

Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense, and factual knowledge. One form of knowledge that has not been studied yet in this context is information about the scalar magnitudes of…

Computation and Language · Computer Science 2020-11-25 Xikun Zhang , Deepak Ramachandran , Ian Tenney , Yanai Elazar , Dan Roth

Multilingual models are often particularly dependent on scaling to generalize to a growing number of languages. Compression techniques are widely relied upon to reconcile the growth in model size with real world resource constraints, but…

Computation and Language · Computer Science 2022-11-29 Kelechi Ogueji , Orevaoghene Ahia , Gbemileke Onilude , Sebastian Gehrmann , Sara Hooker , Julia Kreutzer