Related papers: Toxicity Detection with Generative Prompt-based In…
Evidence-enhanced detectors present remarkable abilities in identifying malicious social text. However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors. This paper explores…
In this paper, we study the problem of detecting machine-generated text when the large language model (LLM) it is possibly derived from is unknown. We do so by apply ensembling methods to the outputs from DetectGPT classifiers (Mitchell et…
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most…
Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet most detectors still treat toxicity as an intrinsic property of isolated text. This position paper…
Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…
The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…
Augmenting large language models (LLMs) with user-specific knowledge is crucial for real-world applications, such as personal AI assistants. However, LLMs inherently lack mechanisms for prompt-driven knowledge capture. This paper…
Retrained large language models (LLMs) have become extensively used across various sub-disciplines of natural language processing (NLP). In NLP, text classification problems have garnered considerable focus, but still faced with some…
Risk perception is subjective, and youth's understanding of toxic content differs from that of adults. Although previous research has conducted extensive studies on toxicity detection in social media, the investigation of youth's unique…
Filtering and annotating textual data are routine tasks in many areas, like social media or news analytics. Automating these tasks allows to scale the analyses wrt. speed and breadth of content covered and decreases the manual effort…
Employing language models to generate explanations for an incoming implicit hate post is an active area of research. The explanation is intended to make explicit the underlying stereotype and aid content moderators. The training often…
The proliferation of Internet memes in the age of social media necessitates effective identification of harmful ones. Due to the dynamic nature of memes, existing data-driven models may struggle in low-resource scenarios where only a few…
Warning: this paper includes model outputs showing offensive content. Recent large-scale Visual-Language Generative Models (VLGMs) have achieved unprecedented improvement in multimodal image/text generation. However, these models might also…
Text moderation for user generated content, which helps to promote healthy interaction among users, has been widely studied and many machine learning models have been proposed. In this work, we explore an alternative perspective by…
Using prompts to explore the knowledge contained within pre-trained language models for downstream tasks has now become an active topic. Current prompt tuning methods mostly convert the downstream tasks to masked language modeling problems…
The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access to the model or substantial training, which is impractical…
The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the-blanks problems (e.g., cloze tests) is a natural approach for…
Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment,…
Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly…
As toxic language becomes nearly pervasive online, there has been increasing interest in leveraging the advancements in natural language processing (NLP), from very large transformer models to automatically detecting and removing toxic…