Related papers: Learn to Select: Exploring Label Distribution Dive…

Convolutional Neural Networks (ConvNets) have achieved excellent recognition performance in various visual recognition tasks. A large labeled training set is one of the most important factors for its success. However, it is difficult to…

The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. While recent studies explore leveraging internal representations of language models to…

Multi-label text classification (MLTC) is an attractive and challenging task in natural language processing (NLP). Compared with single-label text classification, MLTC has a wider range of applications in practice. In this paper, we propose…

In-context learning (ICL) is highly sensitive to which demonstrations appear in the prompt, but selecting them is expensive because the space of possible demonstration contexts and combinations is enormous. We argue that demonstration…

Large language models (LLMs) have shown impressive in-context learning (ICL) ability in code generation. LLMs take a prompt consisting of requirement-code examples and a new requirement as input, and output new programs. Existing studies…

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

In multi-label learning, leveraging contrastive learning to learn better representations faces a key challenge: selecting positive and negative samples and effectively utilizing label information. Previous studies selected positive and…

In-context learning (ICL), a predominant trend in instruction learning, aims at enhancing the performance of large language models by providing clear task guidance and examples, improving their capability in task understanding and…

Large language models (LLMs) have shown impressive capabilities across various tasks, but their performance on domain-specific tasks remains limited. While methods like retrieval augmented generation and fine-tuning can help to address…

Large language models (LLMs) using in-context learning (ICL) excel in many tasks without task-specific fine-tuning. However, demonstration selection and ordering greatly impact ICL effectiveness. Focus on this issue, we propose DemoShapley,…

In real-world applications, as data availability increases, obtaining labeled data for machine learning (ML) projects remains challenging due to the high costs and intensive efforts required for data annotation. Many ML projects,…

Multimodal in-context learning (ICL) has emerged as a key capability of Large Vision-Language Models (LVLMs), driven by their increasing scale and applicability. Despite its promise, effective ICL in the multimodal setting remains…

In-context learning (ICL) adapts LLMs by providing demonstrations without fine-tuning the model parameters; however, it does not differentiate between demonstrations and quadratically increases the complexity of Transformer LLMs, exhausting…

The predictions of Large Language Models (LLMs) on downstream tasks often improve significantly when including examples of the input--label relationship in the context. However, there is currently no consensus about how this in-context…

Multi-label text classification (MLC) is a challenging task in settings of large label sets, where label support follows a Zipfian distribution. In this paper, we address this problem through retrieval augmentation, aiming to improve the…

Distance-based unsupervised text classification is a method within text classification that leverages the semantic similarity between a label and a text to determine label relevance. This method provides numerous benefits, including fast…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks without weight updates by learning from demonstration sequences. While ICL shows strong empirical performance, its internal representational mechanisms are…

Text Classification is one of the fundamental tasks in natural language processing, which requires an agent to determine the most appropriate category for input sentences. Recently, deep neural networks have achieved impressive performance…