English
Related papers

Related papers: Simple Text Detoxification by Identifying a Linear…

200 papers

Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…

Computation and Language · Computer Science 2022-03-08 Canwen Xu , Zexue He , Zhankui He , Julian McAuley

Transformer-based Language Models (LMs) have achieved impressive results on natural language understanding tasks, but they can also generate toxic text such as insults, threats, and profanity, limiting their real-world applications. To…

Computation and Language · Computer Science 2023-07-06 Jin Myung Kwak , Minseon Kim , Sung Ju Hwang

Existing studies have investigated the tendency of autoregressive language models to generate contexts that exhibit undesired biases and toxicity. Various debiasing approaches have been proposed, which are primarily categorized into…

Computation and Language · Computer Science 2022-05-03 Yoon A Park , Frank Rudzicz

Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g., alignment) adjust output preferences, they fail to…

Machine Learning · Computer Science 2026-01-13 Zenghao Duan , Zhiyi Yin , Zhichao Shi , Liang Pang , Shaoling Jing , Zihe Huang , Jiayi Wu , Yu Yan , Jingcheng Deng , Huawei Shen , Xueqi Cheng

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…

Computation and Language · Computer Science 2021-11-04 David Dale , Anton Voronov , Daryna Dementieva , Varvara Logacheva , Olga Kozlova , Nikita Semenov , Alexander Panchenko

Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks. However, language models that are pretrained on large unlabeled web text corpora have been shown…

Computation and Language · Computer Science 2022-07-28 Farshid Faal , Ketra Schmitt , Jia Yuan Yu

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,…

Computation and Language · Computer Science 2020-09-29 Samuel Gehman , Suchin Gururangan , Maarten Sap , Yejin Choi , Noah A. Smith

Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale. Detoxification is therefore important for safety and user trust, particularly when we want to reduce harmful…

Computation and Language · Computer Science 2026-02-04 Baturay Saglam , Dionysis Kalogerias

Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often…

Computation and Language · Computer Science 2026-02-09 Himanshu Singh , Ziwei Xu , A. V. Subramanyam , Mohan Kankanhalli

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…

Computation and Language · Computer Science 2025-05-26 Zenghao Duan , Zhiyi Yin , Zhichao Shi , Liang Pang , Shaoling Jing , Jiayi Wu , Yu Yan , Huawei Shen , Xueqi Cheng

The widespread dissemination of toxic content on social media poses a serious threat to both online environments and public discourse, highlighting the urgent need for detoxification methods that effectively remove toxicity while preserving…

Machine Learning · Computer Science 2025-07-08 Jing Yu , Yibo Zhao , Jiapeng Zhu , Wenming Shao , Bo Pang , Zhao Zhang , Xiang Li

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…

Computation and Language · Computer Science 2022-10-25 Boxin Wang , Wei Ping , Chaowei Xiao , Peng Xu , Mostofa Patwary , Mohammad Shoeybi , Bo Li , Anima Anandkumar , Bryan Catanzaro

Existing approaches for Large language model (LLM) detoxification generally rely on training on large-scale non-toxic or human-annotated preference data, designing prompts to instruct the LLM to generate safe content, or modifying the model…

Computation and Language · Computer Science 2025-06-03 Yuanhe Tian , Mingjie Deng , Guoqing Jin , Yan Song

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…

Computation and Language · Computer Science 2021-09-10 Timo Schick , Sahana Udupa , Hinrich Schütze

Understanding toxicity in user conversations is undoubtedly an important problem. Addressing "covert" or implicit cases of toxicity is particularly hard and requires context. Very few previous studies have analysed the influence of…

Computation and Language · Computer Science 2022-10-19 Atijit Anuchitanukul , Julia Ive , Lucia Specia

Interpretations of a single sentence can vary, particularly when its context is lost. This paper aims to simulate how readers perceive content with varying toxicity levels by generating diverse interpretations of out-of-context sentences.…

Computation and Language · Computer Science 2026-04-17 Maria Mihaela Trusca , Liesbeth Allein

Detoxification is a task of generating text in polite style while preserving meaning and fluency of the original toxic text. Existing detoxification methods are designed to work in one exact language. This work investigates multilingual and…

Computation and Language · Computer Science 2022-06-07 Daniil Moskovskiy , Daryna Dementieva , Alexander Panchenko

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…

Computation and Language · Computer Science 2026-05-28 Himanshu Beniwal , Mayank Singh

The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…

Computation and Language · Computer Science 2024-10-31 Feng Yao , Yufan Zhuang , Zihao Sun , Sunan Xu , Animesh Kumar , Jingbo Shang

Large language models (LM) generate remarkably fluent text and can be efficiently adapted across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of safety is imperative for deploying LMs in the real world; to…

‹ Prev 1 2 3 10 Next ›