相关论文: ToXCL: A Unified Framework for Toxic Speech Detect…

Online social media platforms increasingly rely on Natural Language Processing (NLP) techniques to detect abusive content at scale in order to mitigate the harms it causes to their users. However, these techniques suffer from various…

The proliferation of multimodal content on social media presents significant challenges in understanding and moderating complex, context-dependent issues such as misinformation, hate speech, and propaganda. While efforts have been made to…

Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity…

Coherent discourse is distinguished from a mere collection of utterances by the satisfaction of a diverse set of constraints, for example choice of expression, logical relation between denoted events, and implicit compatibility with…

Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context. However, the model often fails to internalize this information into responses in a…

Online conversations can be toxic and subjected to threats, abuse, or harassment. To identify toxic text comments, several deep learning and machine learning models have been proposed throughout the years. However, recent studies…

Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framework that integrates…

The widespread deployment of text-to-image diffusion models is significantly challenged by the generation of visually harmful content, such as sexually explicit content, violence, and horror imagery. Common safety interventions, ranging…

Accurate detection and classification of online hate is a difficult task. Implicit hate is particularly challenging as such content tends to have unusual syntax, polysemic words, and fewer markers of prejudice (e.g., slurs). This problem is…

The proliferation of abusive language in online communications has posed significant risks to the health and wellbeing of individuals and communities. The growing concern regarding online abuse and its consequences necessitates methods for…

Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and seemingly toxic but harmless content being over-detected. We introduce BiasX, a framework…

Understanding causal heterogeneity is essential for scientific discovery in domains such as biology and medicine. However, existing methods lack causal awareness, with insufficient modeling of heterogeneity, confounding, and observational…

Timely assessment of compound toxicity is one of the biggest challenges facing the pharmaceutical industry today. A significant proportion of compounds identified as potential leads are ultimately discarded due to the toxicity they induce.…

When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As…

Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural…

Detecting problematic content, such as hate speech, is a multifaceted and ever-changing task, influenced by social dynamics, user populations, diversity of sources, and evolving language. There has been significant efforts, both in academia…

In the pursuit of developing Large Language Models (LLMs) that adhere to societal standards, it is imperative to detect the toxicity in the generated text. The majority of existing toxicity metrics rely on encoder models trained on specific…

Unsupervised clustering is widely used to explore large corpora, but existing formulations neither consider the users' goals nor explain clusters' meanings. We propose a new task formulation, "Goal-Driven Clustering with Explanations"…

The advent of social media has given rise to numerous ethical challenges, with hate speech among the most significant concerns. Researchers are attempting to tackle this problem by leveraging hate-speech detection and employing language…

Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities. In this paper, we propose VioLA, a single auto-regressive Transformer decoder-only…