Related papers: Grow, Don't Overwrite: Fine-tuning Without Forgett…
To mitigate forgetting, existing lifelong event detection methods typically maintain a memory module and replay the stored memory data during the learning of a new task. However, the simple combination of memory data and new-task samples…
We consider small-data, large-scale decision problems in which a firm must make many operational decisions simultaneously (e.g., across a large product portfolio) while observing only a few, potentially noisy, data points per instance.…
Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…
The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity…
Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.05247) claimed that…
Large language models often struggle with length generalization and solving complex problem instances beyond their training distribution. We present a self-improvement approach where models iteratively generate and learn from their own…
Fine-tuning large language models on new data improves task performance but degrades capabilities learned during pretraining, a phenomenon known as catastrophic forgetting. Existing methods mitigate this by modifying the fine-tuning…
Loss of plasticity is one of the main challenges in continual learning with deep neural networks, where neural networks trained via backpropagation gradually lose their ability to adapt to new tasks and perform significantly worse than…
Deep transfer learning techniques try to tackle the limitations of deep learning, the dependency on extensive training data and the training costs, by reusing obtained knowledge. However, the current DTL techniques suffer from either…
Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…
Generally intelligent agents exhibit successful behavior across problems in several settings. Endemic in approaches to realize such intelligence in machines is catastrophic forgetting: sequential learning corrupts knowledge obtained earlier…
Fine-tuning has been proven to be a simple and effective technique to transfer the learned knowledge of Pre-trained Language Models (PLMs) to downstream tasks. However, vanilla fine-tuning easily overfits the target data and degrades the…
Fine-tuning a pretrained transformer for a downstream task has become a standard method in NLP in the last few years. While the results from these models are impressive, applying them can be extremely computationally expensive, as is…
In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…
Multi-Task Learning (MTL) is widely-accepted in Natural Language Processing as a standard technique for learning multiple related tasks in one model. Training an MTL model requires having the training data for all tasks available at the…
Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…
Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspective is incomplete, because uncertainty reliability can degrade earlier and more sharply…
Open-sourcing foundation models (FMs) enables broad reuse but also exposes model trainers to economic and safety risks from unrestricted downstream fine-tuning. We address this problem by building non-fine-tunable foundation models: models…
In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the…
Fine-tuning Multimodal Large Language Models (MLLMs) on task-specific data is an effective way to improve performance on downstream applications. However, such adaptation often leads to a degradation in generalization on pretrained tasks, a…