English
Related papers

Related papers: Reward Modeling for Mitigating Toxicity in Transfo…

200 papers

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…

Computation and Language · Computer Science 2025-09-23 Zuhair Hasan Shaik , Abdullah Mazhar , Aseem Srivastava , Md Shad Akhtar

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…

Computation and Language · Computer Science 2021-12-16 Andrew Wang , Mohit Sudhakar , Yangfeng Ji

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…

Computation and Language · Computer Science 2024-01-17 Tong Niu , Caiming Xiong , Semih Yavuz , Yingbo Zhou

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

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…

Computation and Language · Computer Science 2025-05-29 Yifan Lu , Jing Li , Yigeng Zhou , Yihui Zhang , Wenya Wang , Xiucheng Li , Meishan Zhang , Fangming Liu , Jun Yu , Min Zhang

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…

Artificial Intelligence · Computer Science 2026-02-02 Danqing Chen , Tobias Ladner , Ahmed Rayen Mhadhbi , Matthias Althoff

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…

Computation and Language · Computer Science 2023-11-27 Daryna Dementieva , Daniil Moskovskiy , David Dale , Alexander Panchenko

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…

Computation and Language · Computer Science 2021-02-02 Xuhui Zhou , Maarten Sap , Swabha Swayamdipta , Noah A. Smith , Yejin Choi

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

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,…

Computation and Language · Computer Science 2024-08-20 Rameez Qureshi , Naïm Es-Sebbani , Luis Galárraga , Yvette Graham , Miguel Couceiro , Zied Bouraoui

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…

Computation and Language · Computer Science 2021-06-15 Yung-Sung Chuang , Mingye Gao , Hongyin Luo , James Glass , Hung-yi Lee , Yun-Nung Chen , Shang-Wen Li

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

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…

Computation and Language · Computer Science 2026-01-12 Abayomi O. Agbeyangi

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

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…

Computation and Language · Computer Science 2023-06-05 Zonghan Yang , Xiaoyuan Yi , Peng Li , Yang Liu , Xing Xie

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…

Computation and Language · Computer Science 2026-04-22 Wei Shao , Yihang Wang , Gaoyu Zhu , Ziqiang Cheng , Lei Yu , Jiafeng Guo , Xueqi Cheng

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,…

Computation and Language · Computer Science 2024-05-31 Luiza Pozzobon , Patrick Lewis , Sara Hooker , Beyza Ermis

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…

Computation and Language · Computer Science 2025-06-02 Tassilo Klein , Moin Nabi

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…

Artificial Intelligence · Computer Science 2025-02-12 Huanqian Wang , Yang Yue , Rui Lu , Jingxin Shi , Andrew Zhao , Shenzhi Wang , Shiji Song , Gao Huang