Diffusion models produce impressive results in modalities ranging from images and video to
protein design and text. However, generating samples with user-specified properties …

Multilingual text detoxification is a style transfer task of creating neutral versions of toxic texts
across multiple languages. In this paper, we use a mix of real and synthetic data to build a …

Addressing the pervasive issue of toxicity in online communication requires innovative
solutions beyond mere identification and removal of harmful content. This paper presents …

The task of text detoxification aims to re-write toxic text into non-toxic text. Though existing
methods have achieved impressive detoxification performance in monolingual settings …

Multilingual text detoxification is a natural language processing downstream task that inputs
toxic sentences, and then outputs a neutral version that preserves the original meaning and …

Even with various regulations in place across countries and social media platforms
(Government of India, 2021; European Parliament and Council of the European Union …

Despite their impressive capabilities, large language models (LLMs) often lack
interpretability and can generate toxic content. While using LLMs as foundation models and …

The rapid advancement of large language models (LLMs) has increased the need for
guardrail models to ensure responsible use, particularly in detecting unsafe and illegal …

Abstract Large Language Models (LLMs) have significantly altered the landscape of Natural
Language Processing (NLP), having topped the benchmarks of many standard tasks and …

The TextClass Benchmark project is an ongoing, continuous benchmarking process that
aims to provide a comprehensive, fair, and dynamic evaluation of LLMs and transformers for …