相关论文: Reward Modeling for Mitigating Toxicity in Transfo…
Large Language Models have demonstrated impressive fluency across diverse tasks, yet their tendency to produce toxic content remains a critical challenge for AI safety and public trust. Existing toxicity mitigation approaches primarily…
Large pre-trained language models are often trained on large volumes of internet data, some of which may contain toxic or abusive language. Consequently, language models encode toxic information, which makes the real-world usage of these…
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…
Pre-trained language models (LMs) are shown to easily generate toxic language. In this work, we systematically explore domain-adaptive training to reduce the toxicity of language models. We conduct this study on three dimensions: training…
Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning…
Large language models (LLMs) exhibit impressive language capabilities but remain vulnerable to malicious prompts and jailbreaking attacks. Existing knowledge editing methods for LLM detoxification face two major challenges. First, they…
As large language models become integral to high-stakes applications, ensuring their robustness and fairness is critical. Despite their success, large language models remain vulnerable to adversarial attacks, where small perturbations, such…
Text detoxification is the task of transferring the style of text from toxic to neutral. While here are approaches yielding promising results in monolingual setup, e.g., (Dale et al., 2021; Hallinan et al., 2022), cross-lingual transfer for…
Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text…
Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language,…
With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…
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…
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…
Toxic language is one of the major barrier to safe online participation, yet robust mitigation tools are scarce for African languages. This study addresses this critical gap by investigating automatic text detoxification (toxic to neutral…
We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models…
Warning: this paper contains model outputs exhibiting offensiveness and biases. Recently pre-trained language models (PLMs) have prospered in various natural language generation (NLG) tasks due to their ability to generate fairly fluent…
Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself. Such training-based or controllable decoding approaches…
To date, toxicity mitigation in language models has almost entirely been focused on single-language settings. As language models embrace multilingual capabilities, it's crucial our safety measures keep pace. Recognizing this research gap,…
The generation of toxic content by large language models (LLMs) remains a critical challenge for the safe deployment of language technology. We propose a novel framework for implicit knowledge editing and controlled text generation by…
Large Language Models (LLMs) have demonstrated great potential as generalist assistants, showcasing powerful task understanding and problem-solving capabilities. To deploy LLMs as AI assistants, it is crucial that these models exhibit…