相关论文: Large, Small or Both: A Novel Data Augmentation Fr…

Despite the rapid growth in model architecture, the scarcity of large parallel corpora remains the main bottleneck in Neural Machine Translation. Data augmentation is a technique that enhances the performance of data-hungry models by…

Large Language Models have been shown to demonstrate stereotypical biases in their representations and behavior due to the discriminative nature of the data that they have been trained on. Despite significant progress in the development of…

Topic-controlled summarisation enables users to generate summaries focused on specific aspects of source documents. This paper investigates a data augmentation strategy for training small language models (sLMs) to perform topic-controlled…

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…

Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting…

Accurate assessment of cognitive decline from spontaneous speech remains challenging due to limited dataset size and class imbalance. In this work, we propose a large language model (LLM)-driven data augmentation framework to improve the…

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases, raising fairness concerns. Existing debiasing methods, such…

Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents, such as user reviews of a product. The task is practically important and has attracted a lot of attention. However,…

Large language model (LLM) is an effective approach to addressing data scarcity in low-resource scenarios. Recent existing research designs hand-crafted prompts to guide LLM for data augmentation. We introduce a data augmentation strategy…

Large language models (LLMs) have achieved promising results in sentiment analysis through the in-context learning (ICL) paradigm. However, their ability to distinguish subtle sentiments still remains a challenge. Inspired by the human…

For text classification tasks, finetuned language models perform remarkably well. Yet, they tend to rely on spurious patterns in training data, thus limiting their performance on out-of-distribution (OOD) test data. Among recent models…

Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples. However, in opinion summarization, large annotated datasets of reviews…

Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence, garnering significant interest from both academic and industrial spheres. However, the training of…

The construction of open-domain dialogue systems requires high-quality dialogue datasets. The dialogue data admits a wide variety of responses for a given dialogue history, especially responses with different semantics. However, collecting…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Thought (CoT) process, leading to continuous "Bias Propagation". Existing debiasing methods…

Despite the impressive performance of large multimodal models (LMMs) in high-level visual tasks, their capacity for image quality assessment (IQA) remains limited. One main reason is that LMMs are primarily trained for high-level tasks…

Recently, opinion summarization, which is the generation of a summary from multiple reviews, has been conducted in a self-supervised manner by considering a sampled review as a pseudo summary. However, non-text data such as image and…

While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for…

With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating social problems such as hatred, racism, and sexism. Detecting offensive language use is…