Related papers: Large, Small or Both: A Novel Data Augmentation Fr…
Warning: This paper contains content that may be offensive or upsetting. There has been a significant increase in the usage of large language models (LLMs) in various applications, both in their original form and through fine-tuned…
Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from training corpora, they may produce hallucinations, stereotypes,…
With the rapid development of the internet, the richness of User-Generated Contentcontinues to increase, making Multimodal Aspect-Based Sentiment Analysis (MABSA) a research hotspot. Existing studies have achieved certain results in MABSA,…
With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…
In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…
Large language models exhibit societal biases associated with demographic information, including race, gender, and others. Endowing such language models with personalities based on demographic data can enable generating opinions that align…
Opinion summarization is the task of automatically creating summaries that reflect subjective information expressed in multiple documents, such as product reviews. While the majority of previous work has focused on the extractive setting,…
Data augmentation is a critical component of deep learning pipelines, enhancing model generalization by increasing dataset diversity. Traditional augmentation strategies rely on manually designed transformations, stochastic sampling, or…
Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…
As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with…
Abstractive summarization systems based on pretrained language models often generate coherent but factually inconsistent sentences. In this paper, we present a counterfactual data augmentation approach where we augment data with perturbed…
Large Language Models~(LLMs) struggle with providing current information due to the outdated pre-training data. Existing methods for updating LLMs, such as knowledge editing and continual fine-tuning, have significant drawbacks in…
Sentiment analysis plays a crucial role in understanding the sentiment expressed in text data. While sentiment analysis research has been extensively conducted in English and other Western languages, there exists a significant gap in…
A challenge in mitigating social bias in fine-tuned language models (LMs) is the potential reduction in language modeling capability, which can harm downstream performance. Counterfactual data augmentation (CDA), a widely used method for…
Sentiment analysis is a common task in natural language processing that aims to detect polarity of a text document (typically a consumer review). In the simplest settings, we discriminate only between positive and negative sentiment,…
This work introduces a Bayesian framework that unifies a wide class of opinion dynamics models. In this framework, an individual's opinion on a topic is the expected value of their belief, represented as a random variable with a prior…
Aspect-based-sentiment-analysis (ABSA) is a fine-grained sentiment evaluation task, which analyzes the emotional polarity of the evaluation aspects. Generally, the emotional polarity of an aspect exists in the corresponding opinion…
Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…
In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…
We introduce context augmentation, a data-augmentation approach that uses large language models (LLMs) to generate contexts around observed strings as a means of facilitating valid frequentist inference. These generated contexts serve to…