English
Related papers

Related papers: Where Does Toxicity Live? Mechanistic Localization…

200 papers

Large Language Models (LLMs) trained on web-scale corpora inherently absorb toxic patterns from their training data. This leads to toxic degeneration where even innocuous prompts can trigger harmful outputs. This phenomenon poses…

Computation and Language · Computer Science 2026-05-18 Mokshit Surana , Archit Rathod , Akshaj Satishkumar

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Computation and Language · Computer Science 2023-11-30 Jiaxin Wen , Pei Ke , Hao Sun , Zhexin Zhang , Chengfei Li , Jinfeng Bai , Minlie Huang

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

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely…

Computation and Language · Computer Science 2025-10-20 Zhiqiang Kou , Junyang Chen , Xin-Qiang Cai , Ming-Kun Xie , Biao Liu , Changwei Wang , Lei Feng , Yuheng Jia , Gang Niu , Masashi Sugiyama , Xin Geng

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

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

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

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

In recent years, the advent of the attention mechanism has significantly advanced the field of natural language processing (NLP), revolutionizing text processing and text generation. This has come about through transformer-based…

Computation and Language · Computer Science 2026-01-13 Zhiyao Zhang , Yazan Mash'Al , Yuhan Wu

The problem of data contamination is now almost inevitable during the development of large language models (LLMs), with the training data commonly integrating those evaluation benchmarks even unintentionally. This problem subsequently makes…

Computation and Language · Computer Science 2025-09-19 Ruijie Hou , Yueyang Jiao , Hanxu Hu , Yingming Li , Wai Lam , Huajian Zhang , Hongyuan Lu

How to defend large language models (LLMs) from generating toxic content is an important research area. Yet, most research focused on various model training techniques to remediate LLMs by updating their weights. A typical related research…

Computation and Language · Computer Science 2026-05-21 Hongyuan Lu , Wai Lam

Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a method of generating…

Computation and Language · Computer Science 2019-12-17 Keita Kurita , Anna Belova , Antonios Anastasopoulos

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

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

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

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

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

Toxicity classification for voice heavily relies on the semantic content of speech. We propose a novel framework that utilizes cross-modal learning to integrate the semantic embedding of text into a multilabel speech toxicity classifier…

Computation and Language · Computer Science 2024-11-19 Joseph Liu , Mahesh Kumar Nandwana , Janne Pylkkönen , Hannes Heikinheimo , Morgan McGuire

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…

The proliferation of online toxic speech is a pertinent problem posing threats to demographic groups. While explicit toxic speech contains offensive lexical signals, implicit one consists of coded or indirect language. Therefore, it is…

Computation and Language · Computer Science 2024-05-21 Nhat M. Hoang , Xuan Long Do , Duc Anh Do , Duc Anh Vu , Luu Anh Tuan