相关论文: Shortcut Solutions Learned by Transformers Impair …

Continual Learning (CL) methods usually learn from all available data. However, this is not the case in human cognition which efficiently focuses on key experiences while disregarding the redundant information. Similarly, not all data…

Humans exhibit remarkable compositional reasoning by integrating knowledge from various sources. For example, if someone learns ( B = f(A) ) from one source and ( C = g(B) ) from another, they can deduce ( C=g(B)=g(f(A)) ) even without…

Recent studies have discovered that Chain-of-Thought prompting (CoT) can dramatically improve the performance of Large Language Models (LLMs), particularly when dealing with complex tasks involving mathematics or reasoning. Despite the…

Continual Learning (CL) seeks to enable neural networks to incrementally acquire new knowledge (plasticity) while retaining existing knowledge (stability). Although pre-trained models (PTMs) have provided a strong foundation for CL,…

Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn…

This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on ASC. A CL…

Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable…

Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However,…

The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the…

Pretrained deep contextual representations have advanced the state-of-the-art on various commonsense NLP tasks, but we lack a concrete understanding of the capability of these models. Thus, we investigate and challenge several aspects of…

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…

The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions. While the importance…

Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn new tasks and overcome forgetting the knowledge obtained from the…

Using task-specific components within a neural network in continual learning (CL) is a compelling strategy to address the stability-plasticity dilemma in fixed-capacity models without access to past data. Current methods focus only on…

Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old data, replay-based…

Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static…

"You never forget how to ride a bike", -- but how is that possible? The brain is able to learn complex skills, stop the practice for years, learn other skills in between, and still retrieve the original knowledge when necessary. The…

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

Recent studies have highlighted the limitations of large language models in mathematical reasoning, particularly their inability to capture the underlying logic. Inspired by meta-learning, we propose that models should acquire not only…

Heavily pre-trained transformer models such as BERT have recently shown to be remarkably powerful at language modelling by achieving impressive results on numerous downstream tasks. It has also been shown that they are able to implicitly…