Related papers: Reward Modeling for Mitigating Toxicity in Transfo…

Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-level filtering with no mechanistic insight into where toxicity originates internally. We…

Language models are the new state-of-the-art natural language processing (NLP) models and they are being increasingly used in many NLP tasks. Even though there is evidence that language models are biased, the impact of that bias on the…

Considerable effort has been dedicated to mitigating toxicity, but existing methods often require drastic modifications to model parameters or the use of computationally intensive auxiliary models. Furthermore, previous approaches have…

With the recent rise of toxicity in online conversations on social media platforms, using modern machine learning algorithms for toxic comment detection has become a central focus of many online applications. Researchers and companies have…

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Detoxification in large language models (LLMs) remains a significant research challenge. Existing decoding detoxification methods are all based on external constraints, which require additional resource overhead and lose generation fluency.…

The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from…

While large language models (LLMs) have increasingly been applied to hate speech detoxification, the prompts often trigger safety alerts, causing LLMs to refuse the task. In this study, we systematically investigate false refusal behavior…

Current large-scale language models can be politically biased as a result of the data they are trained on, potentially causing serious problems when they are deployed in real-world settings. In this paper, we describe metrics for measuring…

Lack of moderation in online communities enables participants to incur in personal aggression, harassment or cyberbullying, issues that have been accentuated by extremist radicalisation in the contemporary post-truth politics scenario. This…

Large pre-trained language models are successfully being used in a variety of tasks, across many languages. With this ever-increasing usage, the risk of harmful side effects also rises, for example by reproducing and reinforcing…

This paper investigates the underlying mechanisms of toxicity generation in Large Language Models (LLMs) and proposes an effective detoxification approach. Prior work typically considers the Feed-Forward Network (FFN) as the main source of…

The evolution of digital communication systems and the designs of online platforms have inadvertently facilitated the subconscious propagation of toxic behavior. Giving rise to reactive responses to toxic behavior. Toxicity in online…

Toxicity is a prevalent social behavior that involves the use of hate speech, offensive language, bullying, and abusive speech. While text-based approaches for toxicity detection are common, there is limited research on processing speech…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Text detoxification has the potential to mitigate the harms of toxicity by rephrasing text to remove offensive meaning, but subtle toxicity remains challenging to tackle. We introduce MaRCo, a detoxification algorithm that combines…

Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address these issues by identifying and penalizing undesirable…

As large language models (LLMs) become increasingly prevalent in global applications, ensuring that they are toxicity-free across diverse linguistic contexts remains a critical challenge. We explore "Cross-lingual Detoxification", a…

Large-scale language models often learn behaviors that are misaligned with user expectations. Generated text may contain offensive or toxic language, contain significant repetition, or be of a different sentiment than desired by the user.…

Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and similar algorithms, reduce the likelihood of harmful…