Related papers: How Few-Shot Examples Add Up: A Causal Decompositi…

Standard few-shot relation classification (RC) is designed to learn a robust classifier with only few labeled data for each class. However, previous works rarely investigate the effects of a different number of classes (i.e., $N$-way) and…

In-context learning (ICL) has proven to be an effective strategy for improving the performance of large language models (LLMs) with no additional training. However, the exact mechanism behind this performance improvement remains unclear.…

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make…

Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted. While this might be acceptable in many classification scenarios, it poses a…

Recent studies have shown that Large Language Models (LLMs) can improve their reasoning performance through self-generated few-shot examples, achieving results comparable to manually curated in-context examples. However, the underlying…

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 learning (FSL) has attracted considerable attention recently. Among existing approaches, the metric-based method aims to train an embedding network that can make similar samples close while dissimilar samples as far as possible and…

Pre-trained language models (PLMs) have exhibited remarkable few-shot learning capabilities when provided a few examples in a natural language prompt as demonstrations of test instances, i.e., in-context learning. However, the performance…

Integrating image and text data through multi-modal learning has emerged as a new approach in medical imaging research, following its successful deployment in computer vision. While considerable efforts have been dedicated to establishing…

In-context learning (ICL) can significantly enhance the complex reasoning capabilities of large language models (LLMs), with the key lying in the selection and ordering of demonstration examples. Previous methods typically relied on simple…

Large Language Models (LLMs) can perform new tasks from in-context demonstrations, a phenomenon known as in-context learning (ICL). Recent work suggests that these demonstrations are compressed into task vectors (TVs), compact task…

Visual In-Context Learning (VICL) has emerged as a powerful paradigm, enabling models to perform novel visual tasks by learning from in-context examples. The dominant "retrieve-then-prompt" approach typically relies on selecting the single…

Recent advances in large language models (LLMs) enable effective in-context learning (ICL) with many-shot examples, but at the cost of high computational demand due to longer input tokens. To address this, we propose cheat-sheet ICL, which…

In-context learning (ICL) enables large language models to perform new tasks by conditioning on a sequence of examples. Most prior work reasonably and intuitively assumes that which examples are chosen has a far greater effect on…

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the…

Modern language models (LMs) can learn to perform new tasks in different ways: in instruction following, the target task is described explicitly in natural language; in few-shot prompting, the task is specified implicitly with a small…

We argue that in-context learning (ICL) predictably arises from standard self-supervised next-token pretraining, rather than being an exotic emergent property. This work establishes the foundational principles of this emergence by focusing…

Transformer-based language models have achieved remarkable success in few-shot in-context learning and drawn a lot of research interest. However, these models' performance greatly depends on the choice of the example prompts and also has…

Within few-shot learning, in-context learning (ICL) has become a potential method for leveraging contextual information to improve model performance on small amounts of data or in resource-constrained environments where training models on…

Contrastive Language-Image Pre-training (CLIP) has shown powerful zero-shot learning performance. Few-shot learning aims to further enhance the transfer capability of CLIP by giving few images in each class, aka 'few shots'. Most existing…