English
Related papers

Related papers: Preventing Catastrophic Forgetting: Behavior-Aware…

200 papers

Catastrophic forgetting in deep neural networks occurs when learning new tasks degrades performance on previously learned tasks due to knowledge overwriting. Among the approaches to mitigate this issue, regularization techniques aim to…

Machine Learning · Computer Science 2025-07-14 Idan Mashiach , Oren Glickman , Tom Tirer

Training large language models to follow instructions makes them perform better on a wide range of tasks and generally become more helpful. However, a perfectly helpful model will follow even the most malicious instructions and readily…

Computation and Language · Computer Science 2024-03-20 Federico Bianchi , Mirac Suzgun , Giuseppe Attanasio , Paul Röttger , Dan Jurafsky , Tatsunori Hashimoto , James Zou

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.…

Computation and Language · Computer Science 2025-10-20 Jessy Lin , Luke Zettlemoyer , Gargi Ghosh , Wen-Tau Yih , Aram Markosyan , Vincent-Pierre Berges , Barlas Oğuz

Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact be favorable to learning. We introduce "forget-and-relearn" as a powerful paradigm for shaping the…

Machine Learning · Computer Science 2022-02-02 Hattie Zhou , Ankit Vani , Hugo Larochelle , Aaron Courville

Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks. Our goal is to understand whether a related phenomenon occurs when data does not…

Continual learning is the process of training machine learning models on a sequence of tasks where data distributions change over time. A well-known obstacle in this setting is catastrophic forgetting, a phenomenon in which a model…

Machine Learning · Computer Science 2025-02-18 Andrii Krutsylo

Pretraining language models on large text corpora is a common practice in natural language processing. Fine-tuning of these models is then performed to achieve the best results on a variety of tasks. In this paper, we investigate the…

Computation and Language · Computer Science 2024-04-03 Philip Kenneweg , Alexander Schulz , Sarah Schröder , Barbara Hammer

Large language models (LLMs) and multimodal models (MMs) have exhibited impressive capabilities in various domains, particularly in general language understanding and visual reasoning. However, these models, trained on massive data, may not…

Computation and Language · Computer Science 2024-12-19 Xinbo Wu , Max Hartman , Vidhata Arjun Jayaraman , Lav R. Varshney

Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this…

Machine Learning · Computer Science 2025-12-04 Howard Chen , Noam Razin , Karthik Narasimhan , Danqi Chen

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay,…

Machine Learning · Computer Science 2026-05-08 Yazheng Liu , Yuxuan Wan , Rui Xu , Xi Zhang , Sihong Xie , Hui Xiong

Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning…

Machine Learning · Computer Science 2018-05-30 Joan Serrà , Dídac Surís , Marius Miron , Alexandros Karatzoglou

In this paper, we explore the challenging problem of performing a generative task in a target language when labeled data is only available in English, using summarization as a case study. We assume a strict setting with no access to…

Computation and Language · Computer Science 2022-10-25 Tu Vu , Aditya Barua , Brian Lester , Daniel Cer , Mohit Iyyer , Noah Constant

Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using…

Computation and Language · Computer Science 2026-05-22 Nicola Milano , Davide Marocco

Artificial neural networks (ANNs) suffer from catastrophic forgetting when trained on a sequence of tasks. While this phenomenon was studied in the past, there is only very limited recent research on this phenomenon. We propose a method for…

Machine Learning · Computer Science 2019-06-07 Felix Wiewel , Bin Yang

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In…

Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its…

Artificial Intelligence · Computer Science 2020-02-11 Giacomo Spigler

Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effectively identify clean hard examples with large losses, which…

Machine Learning · Computer Science 2023-08-29 Suqin Yuan , Lei Feng , Tongliang Liu

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content)…

Machine Learning · Computer Science 2024-08-21 Luxi He , Mengzhou Xia , Peter Henderson

Catastrophic forgetting is a problem caused by neural networks' inability to learn data in sequence. After learning two tasks in sequence, performance on the first one drops significantly. This is a serious disadvantage that prevents many…

Machine Learning · Computer Science 2020-04-30 Wojciech Masarczyk , Ivona Tautkute

Existing studies addressing gender bias of pre-trained language models, usually build a small gender-neutral data set and conduct a second phase pre-training on the model with such data. However, given the limited size and concentrated…

Computation and Language · Computer Science 2023-07-03 Zahra Fatemi , Chen Xing , Wenhao Liu , Caiming Xiong