English
Related papers

Related papers: Reawakening knowledge: Anticipatory recovery from …

200 papers

Using neural networks in the reinforcement learning (RL) framework has achieved notable successes. Yet, neural networks tend to forget what they learned in the past, especially when they learn online and fully incrementally, a setting in…

Artificial Intelligence · Computer Science 2022-05-03 Yat Long Lo , Sina Ghiassian

Large language models (LLMs) are often fine-tuned for use on downstream tasks, though this can degrade capabilities learned during previous training. This phenomenon, often referred to as catastrophic forgetting, has important potential…

Computation and Language · Computer Science 2024-12-30 Megan Ung , Alicia Sun , Samuel J. Bell , Bhaktipriya Radharapu , Levent Sagun , Adina Williams

Catastrophic interference, also known as catastrophic forgetting, is a fundamental challenge in machine learning, where a trained learning model progressively loses performance on previously learned tasks when adapting to new ones. In this…

Machine Learning · Computer Science 2025-10-08 Yuke Li , Yujia Zheng , Tianyi Xiong , Zhenyi Wang , Heng Huang

Large language models exhibit remarkable performance across diverse tasks through pre-training and fine-tuning paradigms. However, continual fine-tuning on sequential tasks induces catastrophic forgetting, where newly acquired knowledge…

Machine Learning · Computer Science 2026-01-27 Olaf Yunus Laitinen Imanov

We propose incremental (re)training of a neural network model to cope with a continuous flow of new data in inference during model serving. As such, this is a life-long learning process. We address two challenges of life-long retraining:…

Machine Learning · Computer Science 2020-04-30 Diego Klabjan , Xiaofeng Zhu

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a…

Computation and Language · Computer Science 2026-05-11 Behzad Shayegh , Mohamed Osama Ahmed , Fred Tung , Leo Feng

While Large Language Models (LLMs) acquire vast knowledge during pre-training, they often lack domain-specific, new, or niche information. Continual pre-training (CPT) attempts to address this gap but suffers from catastrophic forgetting…

Computation and Language · Computer Science 2025-04-09 Oded Ovadia , Meni Brief , Rachel Lemberg , Eitam Sheetrit

Deep neural networks are becoming increasingly pervasive in academia and industry, matching and surpassing human performance on a wide variety of fields and related tasks. However, just as humans, even the largest artificial neural networks…

Machine Learning · Computer Science 2024-09-02 Vittorio Mazzia , Alessandro Pedrani , Andrea Caciolai , Kay Rottmann , Davide Bernardi

While modern deep networks have demonstrated remarkable versatility, their training dynamics remain poorly understood--often driven more by empirical tweaks than architectural insight. This paper investigates how internal structural choices…

Machine Learning · Computer Science 2025-08-26 Saleh Nikooroo , Thomas Engel

To what extent can a neural network systematically reason over symbolic facts? Evidence suggests that large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is difficult to control. Recently, it has been…

Computation and Language · Computer Science 2020-11-17 Alon Talmor , Oyvind Tafjord , Peter Clark , Yoav Goldberg , Jonathan Berant

While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There…

Computation and Language · Computer Science 2021-09-10 Xiaoyu Yang , Xiaodan Zhu , Zhan Shi , Tianda Li

Humans can continuously learn new knowledge. However, machine learning models suffer from drastic dropping in performance on previous tasks after learning new tasks. Cognitive science points out that the competition of similar knowledge is…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Runqi Wang , Yuxiang Bao , Baochang Zhang , Jianzhuang Liu , Wentao Zhu , Guodong Guo

Rapid and accurate situational awareness is essential for effective response during natural disasters, where delays in analysis can significantly hinder decision-making. Training task-specific models for post-disaster assessment is often…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Armin Zarbaft , Ehsan Karimi , Nhut Le , Maryam Rahnemoonfar

Pre-training GNNs to extract transferable knowledge and apply it to downstream tasks has become the de facto standard of graph representation learning. Recent works focused on designing self-supervised pre-training tasks to extract useful…

Machine Learning · Computer Science 2024-04-24 Zhe Zhao , Pengkun Wang , Xu Wang , Haibin Wen , Xiaolong Xie , Zhengyang Zhou , Qingfu Zhang , Yang Wang

Training data plays a crucial role in Large Language Models (LLM) scaling, yet high quality data is of limited supply. Synthetic data techniques offer a potential path toward sidestepping these limitations. We conduct a large-scale…

Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task. Here, we propose a method, i.e. incremental moment matching (IMM), to resolve this problem. IMM…

Machine Learning · Computer Science 2018-01-31 Sang-Woo Lee , Jin-Hwa Kim , Jaehyun Jun , Jung-Woo Ha , Byoung-Tak Zhang

Continual Pre-Training (CPT) is widely used for acquiring and updating factual knowledge in LLMs. This practice treats loss as a proxy for knowledge learning, while offering no grounding into how it changes during training. We study CPT as…

Computation and Language · Computer Science 2026-01-08 Seyed Mahed Mousavi , Simone Alghisi , Giuseppe Riccardi

Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly how to structurally embed acquired knowledge in their neural…

Machine Learning · Computer Science 2025-06-03 Yixin Ou , Yunzhi Yao , Ningyu Zhang , Hui Jin , Jiacheng Sun , Shumin Deng , Zhenguo Li , Huajun Chen

Neural networks are increasingly employed to model, analyze and control non-linear dynamical systems ranging from physics to biology. Owing to their universal approximation capabilities, they regularly outperform state-of-the-art…

Dynamical Systems · Mathematics 2023-12-27 Alessandro Corbetta , Thomas Geert de Jong

While recurrent neural networks have found success in a variety of natural language processing applications, they are general models of sequential data. We investigate how the properties of natural language data affect an LSTM's ability to…

Computation and Language · Computer Science 2019-04-09 Nelson F. Liu , Omer Levy , Roy Schwartz , Chenhao Tan , Noah A. Smith
‹ Prev 1 4 5 6 7 8 10 Next ›