Related papers: Toxicity Detection with Generative Prompt-based In…

Interpretations of a single sentence can vary, particularly when its context is lost. This paper aims to simulate how readers perceive content with varying toxicity levels by generating diverse interpretations of out-of-context sentences.…

In this project, we want to explore the newly emerging field of prompt engineering and apply it to the downstream task of detecting LM biases. More concretely, we explore how to design prompts that can indicate 4 different types of biases:…

Recently, prompt-based learning has gained popularity across many natural language processing (NLP) tasks by reformulating them into a cloze-style format to better align pre-trained language models (PLMs) with downstream tasks. However,…

The dissemination of Large Language Models (LLMs), trained at scale, and endowed with powerful text-generating abilities, has made it easier for all to produce harmful, toxic, faked or forged content. In response, various proposals have…

Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori. This is not ideal because in a realworld zero-shot…

The rapid advancement of text-to-image (T2I) models, such as Stable Diffusion, has enhanced their capability to synthesize images from textual prompts. However, this progress also raises significant risks of misuse, including the generation…

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

The advent of Large Language Models LLMs marks a milestone in Artificial Intelligence, altering how machines comprehend and generate human language. However, LLMs are vulnerable to malicious prompt injection attacks, where crafted inputs…

The widespread of generative artificial intelligence has heightened concerns about the potential harms posed by AI-generated texts, primarily stemming from factoid, unfair, and toxic content. Previous researchers have invested much effort…

Vision-Language Models (VLMs), such as CLIP, have significantly advanced zero-shot image recognition. However, their performance remains limited by suboptimal prompt engineering and poor adaptability to target classes. While recent methods…

Creative generation is the synthesis of new, surprising, and valuable samples that reflect user intent yet cannot be envisioned in advance. This task aims to extend human imagination, enabling the discovery of visual concepts that exist in…

In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual assistants. In these dialogues, it is important to identify user's goals automatically to resolve their…

The last few years have witnessed an exponential rise in the propagation of offensive text on social media. Identification of this text with high precision is crucial for the well-being of society. Most of the existing approaches tend to…

Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning…

How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…

The rapid expansion of memes on social media has highlighted the urgent need for effective approaches to detect harmful content. However, traditional data-driven approaches struggle to detect new memes due to their evolving nature and the…

Generating a Chain of Thought (CoT) has been shown to consistently improve large language model (LLM) performance on a wide range of NLP tasks. However, prior work has mainly focused on logical reasoning tasks (e.g. arithmetic, commonsense…

With the widespread availability of LLMs since the release of ChatGPT and increased public scrutiny, commercial model development appears to have focused their efforts on 'safety' training concerning legal liabilities at the expense of…

In the current digitalization era, capturing and effectively representing knowledge is crucial in most real-world scenarios. In this context, knowledge graphs represent a potent tool for retrieving and organizing a vast amount of…

Existing solutions to zero-shot text classification either conduct prompting with pre-trained language models, which is sensitive to the choices of templates, or rely on large-scale annotated data of relevant tasks for meta-tuning. In this…