English
Related papers

Related papers: Redefining Experts: Interpretable Decomposition of…

200 papers

With adversarial or otherwise normal prompts, existing large language models (LLM) can be pushed to generate toxic discourses. One way to reduce the risk of LLMs generating undesired discourses is to alter the training of the LLM. This can…

Computation and Language · Computer Science 2023-02-28 Meng Cao , Mehdi Fatemi , Jackie Chi Kit Cheung , Samira Shabanian

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…

Computation and Language · Computer Science 2025-06-03 Vera Neplenbroek , Arianna Bisazza , Raquel Fernández

Large language models (LLMs) have become integral to our professional workflows and daily lives. Nevertheless, these machine companions of ours have a critical flaw: the huge amount of data which endows them with vast and diverse knowledge,…

Computation and Language · Computer Science 2024-05-21 Tinh Son Luong , Thanh-Thien Le , Linh Ngo Van , Thien Huu Nguyen

Understanding the internal computations of large language models (LLMs) is crucial for aligning them with human values and preventing undesirable behaviors like toxic content generation. However, mechanistic interpretability is hindered by…

Artificial Intelligence · Computer Science 2025-06-12 Jungwoo Park , Young Jin Ahn , Kee-Eung Kim , Jaewoo Kang

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…

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

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

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, yet they remain vulnerable to generating toxic content, necessitating detoxification strategies to ensure safe and responsible deployment. Test-time…

Computation and Language · Computer Science 2025-10-03 Yisong Xiao , Aishan Liu , Siyuan Liang , Zonghao Ying , Xianglong Liu , Dacheng Tao

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

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

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…

Computers and Society · Computer Science 2025-10-01 Smita Khapre , Melkamu Abay Mersha , Hassan Shakil , Jonali Baruah , Jugal Kalita

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

Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrade generation quality or require costly human annotation. We propose CAUSALDETOX, a…

Computation and Language · Computer Science 2026-04-17 Yian Wang , Yuen Chen , Agam Goyal , Hari Sundaram

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…

Cryptography and Security · Computer Science 2023-12-11 Shuli Jiang , Swanand Ravindra Kadhe , Yi Zhou , Ling Cai , Nathalie Baracaldo

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

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

Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal generation but inherit toxic, biased, and NSFW signals from weakly curated pretraining corpora, causing safety…

Computation and Language · Computer Science 2026-02-16 Hongbo Wang , MaungMaung AprilPyone , Isao Echizen

Due to the subtleness, implicity, and different possible interpretations perceived by different people, detecting undesirable content from text is a nuanced difficulty. It is a long-known risk that language models (LMs), once trained on…

Computation and Language · Computer Science 2022-05-26 Yau-Shian Wang , Yingshan Chang

Language models, while capable of generating remarkably coherent and seemingly accurate text, can occasionally produce undesirable content, including harmful or toxic outputs. In this paper, we present a new two-stage approach to detect and…

Machine Learning · Computer Science 2025-11-11 Bao Nguyen , Binh Nguyen , Duy Nguyen , Viet Anh Nguyen