Related papers: Zero-shot Code-Mixed Offensive Span Identification…

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

Recent advances in large language models (LLMs) have demonstrated strong performance on simple text classification tasks, frequently under zero-shot settings. However, their efficacy declines when tackling complex social media challenges…

In this short paper we propose a data augmentation method for intent detection in zero-resource domains. Existing data augmentation methods rely on few labelled examples for each intent category, which can be expensive in settings with many…

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existing approaches require prompt tuning or architectural…

The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks. However, the lack of labelled task data necessitates a variety of methods aiming to close the gap to high-resource…

The widespread presence of offensive language on social media motivated the development of systems capable of recognizing such content automatically. Apart from a few notable exceptions, most research on automatic offensive language…

Cybersecurity is a domain where there is constant change in patterns of attack, and we need ways to make our Cybersecurity systems more adaptive to handle new attacks and categorize for appropriate action. We present a novel approach to…

To combat the potential misuse of Natural Language Generation (NLG) technology, a variety of algorithms have been developed for the detection of AI-generated texts. Traditionally, this task is treated as a binary classification problem.…

Recent research shows that in-context learning (ICL) can be effective even when demonstrations have missing or incorrect labels. To shed light on this capability, we examine a canonical setting where the demonstrations are drawn according…

Explainability algorithms such as LIME have enabled machine learning systems to adopt transparency and fairness, which are important qualities in commercial use cases. However, recent work has shown that LIME's naive sampling strategy can…

Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…

Recent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers due to…

This paper describes an adaptation of the Local Interpretable Model-Agnostic Explanations (LIME) AI method to operate under a biometric verification setting. LIME was initially proposed for networks with the same output classes used for…

Recently efforts have been made by social media platforms as well as researchers to detect hateful or toxic language using large language models. However, none of these works aim to use explanation, additional context and victim community…

Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still…

Code-mixing is a well-studied linguistic phenomenon when two or more languages are mixed in text or speech. Several works have been conducted on building datasets and performing downstream NLP tasks on code-mixed data. Although it is not…

Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples for each user intent. We propose a novel pre-training…

Large-scale contrastive vision-language pre-trained models provide the zero-shot model achieving competitive performance across a range of image classification tasks without requiring training on downstream data. Recent works have confirmed…

Large Language Models (LLMs) demonstrate remarkable potential across various domains; however, they exhibit a significant performance gap in Information Extraction (IE). Note that high-quality instruction data is the vital key for enhancing…