Related papers: Latte: Transfering LLMs` Latent-level Knowledge fo…
Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they leverage all samples of the query set. The two existing classes…
Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words. However, when applied to token-level labeling tasks such as NER, it would…
Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…
Learning clients embeddings from sequences of their historic communications is central to financial applications. While large language models (LLMs) offer general world knowledge, their direct use on long event sequences is computationally…
The goal of few-shot learning is to classify unseen categories with few labeled samples. Recently, the low-level information metric-learning based methods have achieved satisfying performance, since local representations (LRs) are more…
We present a study on the integration of Large Language Models (LLMs) in tabular data classification, emphasizing an efficient framework. Building upon existing work done in TabLLM (arXiv:2210.10723), we introduce three novel serialization…
Over the last couple of years few-shot learning (FSL) has attracted great attention towards minimizing the dependency on labeled training examples. An inherent difficulty in FSL is the handling of ambiguities resulting from having too few…
Automated feature engineering plays a critical role in improving predictive model performance for tabular learning tasks. Traditional automated feature engineering methods are limited by their reliance on pre-defined transformations within…
Large language models (LLMs) provide powerful means to leverage prior knowledge for predictive modeling when data is limited. In this work, we demonstrate how LLMs can use their compressed world knowledge to generate intrinsically…
Few-shot learning deals with problems such as image classification using very few training examples. Recent vision foundation models show excellent few-shot transfer abilities, but are large and slow at inference. Using knowledge…
Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed with the common aim of transferring knowledge acquired on a previously…
Document-level relation extraction aims at inferring structured human knowledge from textual documents. State-of-the-art methods for this task use pre-trained language models (LMs) via fine-tuning, yet fine-tuning is computationally…
Training models on low-resource named entity recognition tasks has been shown to be a challenge, especially in industrial applications where deploying updated models is a continuous effort and crucial for business operations. In such cases…
Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We propose to combine…
In this paper, we introduce the Interpretable Cross-Examination Technique (ICE-T), a novel approach that leverages structured multi-prompt techniques with Large Language Models (LLMs) to improve classification performance over zero-shot and…
We consider the task of few-shot intent detection, which involves training a deep learning model to classify utterances based on their underlying intents using only a small amount of labeled data. The current approach to address this…
Vision Transformers (ViTs) emerge to achieve impressive performance on many data-abundant computer vision tasks by capturing long-range dependencies among local features. However, under few-shot learning (FSL) settings on small datasets…
Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited. Improved performance is possible by transductive inference, where the entire…
Recent instruction-finetuned large language models (LMs) have achieved notable performances in various tasks, such as question-answering (QA). However, despite their ability to memorize a vast amount of general knowledge across diverse…