Related papers: Can In-context Learners Learn a Reasoning Concept …

Few-shot learning aims at recognizing new instances from classes with limited samples. This challenging task is usually alleviated by performing meta-learning on similar tasks. However, the resulting models are black-boxes. There has been…

Few-shot classification tasks aim to classify images in query sets based on only a few labeled examples in support sets. Most studies usually assume that each image in a task has a single and unique class association. Under these…

There has been increasing interest in exploring the capabilities of advanced large language models (LLMs) in the field of information extraction (IE), specifically focusing on tasks related to named entity recognition (NER) and relation…

With in-context learning ability, the performance of large language models can be significantly boosted when provided with appropriate context. However, existing in-context learning methods mainly rely on human-provided contexts, such as…

Few-shot relation extraction involves identifying the type of relationship between two specific entities within a text, using a limited number of annotated samples. A variety of solutions to this problem have emerged by applying…

The majority of existing few-shot learning methods describe image relations with binary labels. However, such binary relations are insufficient to teach the network complicated real-world relations, due to the lack of decision smoothness.…

When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whether and how transformers represent latent structures as part…

Current methods of Visual Question Answering perform well on the answers with an amount of training data but have limited accuracy on the novel ones with few examples. However, humans can quickly adapt to these new categories with just a…

Few-shot image classification consists of two consecutive learning processes: 1) In the meta-learning stage, the model acquires a knowledge base from a set of training classes. 2) During meta-testing, the acquired knowledge is used to…

Humans naturally "program" a fellow collaborator to perform a task by demonstrating the task few times. It is intuitive, therefore, for a human to program a collaborative robot by demonstration and many paradigms use a single demonstration…

Human learning benefits from multi-modal inputs that often appear as rich semantics (e.g., description of an object's attributes while learning about it). This enables us to learn generalizable concepts from very limited visual examples.…

Large-scale models trained on broad data have recently become the mainstream architecture in computer vision due to their strong generalization performance. In this paper, the main focus is on an emergent ability in large vision models,…

Large-scale pretrained language models have led to dramatic improvements in text generation. Impressive performance can be achieved by finetuning only on a small number of instances (few-shot setting). Nonetheless, almost all previous work…

Few-shot and one-shot learning have been the subject of active and intensive research in recent years, with mounting evidence pointing to successful implementation and exploitation of few-shot learning algorithms in practice. Classical…

Concept induction requires the extraction and naming of concepts from noisy perceptual experience. For supervised approaches, as the number of concepts grows, so does the number of required training examples. Philosophers, psychologists,…

Existing approaches to few-shot learning in NLP rely on large language models (LLMs) and/or fine-tuning of these to generalise on out-of-distribution data. In this work, we propose a novel few-shot learning approach based on soft-label…

After discovering that Language Models (LMs) can be good in-context few-shot learners, numerous strategies have been proposed to optimize in-context sequence configurations. Recently, researchers in Vision-Language (VL) domains also develop…

Real-world knowledge graphs are often characterized by low-frequency relations - a challenge that has prompted an increasing interest in few-shot link prediction methods. These methods perform link prediction for a set of new relations,…

In-context learning is a recent paradigm in natural language understanding, where a large pre-trained language model (LM) observes a test instance and a few training examples as its input, and directly decodes the output without any update…

We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to…