Related papers: Redefining Experts: Interpretable Decomposition of…
Detoxifying offensive language while preserving the speaker's original intent is a challenging yet critical goal for improving the quality of online interactions. Although large language models (LLMs) show promise in rewriting toxic…
The widespread adoption of Large Language Models (LLMs) has made the detection of AI-Generated text a pressing and complex challenge. Although many detection systems report high benchmark accuracy, their reliability in real-world settings…
Caution: This paper includes offensive words that could potentially cause unpleasantness. The fast-paced evolution of generative language models such as GPT-4 has demonstrated outstanding results in various NLP generation tasks. However,…
Toxic language detection systems often falsely flag text that contains minority group mentions as toxic, as those groups are often the targets of online hate. Such over-reliance on spurious correlations also causes systems to struggle with…
Multilingual toxicity detection remains a significant challenge due to the scarcity of training data and resources for many languages. While prior work has leveraged the translate-test paradigm to support cross-lingual transfer across a…
This survey paper delves into the emerging and critical area of symbolic knowledge distillation in Large Language Models (LLMs). As LLMs like Generative Pre-trained Transformer-3 (GPT-3) and Bidirectional Encoder Representations from…
The cornerstone of multilingual neural translation is shared representations across languages. Given the theoretically infinite representation power of neural networks, semantically identical sentences are likely represented differently.…
Generative language models have improved drastically, and can now produce realistic text outputs that are difficult to distinguish from human-written content. For malicious actors, these language models bring the promise of automating the…
Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a method of generating…
Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…
Researchers and developers increasingly rely on toxicity scoring to moderate generative language model outputs, in settings such as customer service, information retrieval, and content generation. However, toxicity scoring may render…
Based on official estimates, 50 million people worldwide are affected by dementia, and this number increases by 10 million new patients every year. Without a cure, clinical prognostication and early intervention represent the most effective…
Generating context-aware language that embodies diverse emotions is an important step towards building empathetic NLP systems. In this paper, we propose a formulation of modulated layer normalization -- a technique inspired by computer…
The field of natural language generation has witnessed significant advancements in recent years, including the development of controllable text generation techniques. However, controlling the attributes of the generated text remains a…
Text-to-Image (T2I) models have demonstrated impressive capabilities in generating high-quality and diverse visual content from natural language prompts. However, uncontrolled reproduction of sensitive, copyrighted, or harmful imagery poses…
With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical. Business applications and fundraising in Artificial…
Online toxic content has grown into a pervasive phenomenon, intensifying during times of crisis, elections, and social unrest. A significant amount of research has been focused on detecting or analyzing toxic content using machine-learning…
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…
Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine…
Toxicity detection algorithms, originally designed with reactive content moderation in mind, are increasingly being deployed into proactive end-user interventions to moderate content. Through a socio-technical lens and focusing on contexts…