English
Related papers

Related papers: Revisiting Catastrophic Forgetting in Large Langua…

200 papers

We investigate the performance of DNNs when trained on class-incremental visual problems consisting of initial training, followed by retraining with added visual classes. Catastrophic forgetting (CF) behavior is measured using a new…

Machine Learning · Computer Science 2019-05-21 B. Pfülb , A. Gepperth , S. Abdullah , A. Kilian

Pre-trained Large Language Models (LLMs) require post-training methods such as supervised fine-tuning (SFT) on instruction-response pairs to enable instruction following. However, this process can potentially harm existing capabilities…

Computation and Language · Computer Science 2025-02-04 Yihan Wang , Andrew Bai , Nanyun Peng , Cho-Jui Hsieh

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence due to catastrophic forgetting. Large language models (LLMs) are often impractical to frequent…

Machine Learning · Computer Science 2025-10-28 Jaya Krishna Mandivarapu

Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem in large-scale supervised classification, little has been done to overcome…

Machine Learning · Computer Science 2021-06-22 Pauching Yap , Hippolyt Ritter , David Barber

Federated Learning has been introduced as a new machine learning paradigm enhancing the use of local devices. At a server level, FL regularly aggregates models learned locally on distributed clients to obtain a more general model. In this…

Machine Learning · Computer Science 2022-07-19 Anastasiia Usmanova , François Portet , Philippe Lalanda , German Vega

Machine Unlearning has emerged as a significant area of research, focusing on `removing' specific subsets of data from a trained model. Fine-tuning (FT) methods have become one of the fundamental approaches for approximating unlearning, as…

Machine Learning · Computer Science 2025-11-25 Meng Ding , Rohan Sharma , Changyou Chen , Jinhui Xu , Kaiyi Ji

Large foundation models (LFMs) are claiming incredible performances. Yet great concerns have been raised about their mythic and uninterpreted potentials not only in machine learning, but also in various other disciplines. In this position…

Machine Learning · Computer Science 2024-10-24 Hao Chen , Bhiksha Raj , Xing Xie , Jindong Wang

General-purpose learning systems should improve themselves in open-ended fashion in ever-changing environments. Conventional learning algorithms for neural networks, however, suffer from catastrophic forgetting (CF), i.e., previously…

Machine Learning · Computer Science 2025-02-18 Kazuki Irie , Róbert Csordás , Jürgen Schmidhuber

Catastrophic forgetting remains a critical challenge in the field of continual learning, where neural networks struggle to retain prior knowledge while assimilating new information. Most existing studies emphasize mitigating this issue only…

Machine Learning · Computer Science 2023-09-21 Wenhang Shi , Yiren Chen , Zhe Zhao , Wei Lu , Kimmo Yan , Xiaoyong Du

Pre-trained foundation models, due to their enormous capacity and exposure to vast amounts of data during pre-training, are known to have learned plenty of real-world concepts. An important step in making these pre-trained models effective…

Machine Learning · Computer Science 2024-07-02 Jishnu Mukhoti , Yarin Gal , Philip H. S. Torr , Puneet K. Dokania

Fine-tuning adapts pretrained models for specific tasks but poses the risk of catastrophic forgetting (CF), where critical knowledge from pretraining is overwritten. To address the issue of CF in a general-purpose framework, we propose…

Computation and Language · Computer Science 2025-11-25 Runyu Wang , Peng Ping , Zhengyu Guo , Xiaoye Zhang , Quan Shi , Liting Zhou , Tianbo Ji

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

The cross-lingual transfer is a promising technique to solve tasks in less-resourced languages. In this empirical study, we compare two fine-tuning approaches combined with zero-shot and full-shot learning approaches for large language…

Computation and Language · Computer Science 2025-02-18 Boshko Koloski , Blaž Škrlj , Marko Robnik-Šikonja , Senja Pollak

Deep learning models are prone to forgetting information learned in the past when trained on new data. This problem becomes even more pronounced in the context of federated learning (FL), where data is decentralized and subject to…

Machine Learning · Computer Science 2023-07-19 Sara Babakniya , Zalan Fabian , Chaoyang He , Mahdi Soltanolkotabi , Salman Avestimehr

Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…

Computation and Language · Computer Science 2024-08-09 Tyler Lizzo , Larry Heck

Instruction tuning for large language models (LLMs) can drive them to produce results consistent with human goals in specific downstream tasks. However, the process of continual instruction tuning (CIT) for LLMs may bring about the…

Computation and Language · Computer Science 2025-05-28 Yongquan He , Wenyuan Zhang , Xuancheng Huang , Peng Zhang , Lingxun Meng , Xiang Zhou , Ke Zeng , Xunliang Cai

While deep neural networks have demonstrated groundbreaking performance in various settings, these models often suffer from \emph{catastrophic forgetting} when trained on new tasks in sequence. Several works have empirically demonstrated…

Machine Learning · Computer Science 2024-06-21 Etash Guha , Vihan Lakshman

In Federated Learning, a global model is learned by aggregating model updates computed at a set of independent client nodes, to reduce communication costs multiple gradient steps are performed at each node prior to aggregation. A key…

Machine Learning · Computer Science 2023-04-12 Gwen Legate , Lucas Caccia , Eugene Belilovsky

Unlike primates, training artificial neural networks on changing data distributions leads to a rapid decrease in performance on old tasks. This phenomenon is commonly referred to as catastrophic forgetting. In this paper, we investigate the…

Machine Learning · Computer Science 2023-10-10 Daniel Anthes , Sushrut Thorat , Peter König , Tim C. Kietzmann

Deep neural networks for scene perception in automated vehicles achieve excellent results for the domains they were trained on. However, in real-world conditions, the domain of operation and its underlying data distribution are subject to…

Computer Vision and Pattern Recognition · Computer Science 2023-06-13 Tobias Kalb , Jürgen Beyerer