English
Related papers

Related papers: Leashing the Inner Demons: Self-Detoxification for…

200 papers

We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-level constraint on model outputs, our method fine-tunes the…

Computation and Language · Computer Science 2024-10-10 Tao Meng , Ninareh Mehrabi , Palash Goyal , Anil Ramakrishna , Aram Galstyan , Richard Zemel , Kai-Wei Chang , Rahul Gupta , Charith Peris

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

We propose a self-correction mechanism for Large Language Models (LLMs) to mitigate issues such as toxicity and fact hallucination. This method involves refining model outputs through an ensemble of critics and the model's own feedback.…

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) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

As large language models (LLMs) become increasingly prevalent in global applications, ensuring that they are toxicity-free across diverse linguistic contexts remains a critical challenge. We explore "Cross-lingual Detoxification", a…

Computation and Language · Computer Science 2025-10-24 Himanshu Beniwal , Youngwoo Kim , Maarten Sap , Soham Dan , Thomas Hartvigsen

We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs), based on their outputs, and their internal representations (internals). Using this framework, we examine over 20 OLMo,…

Computation and Language · Computer Science 2025-09-25 Andreas Waldis , Vagrant Gautam , Anne Lauscher , Dietrich Klakow , Iryna Gurevych

Text detoxification aims to minimize the risk of language models producing toxic content. Existing detoxification methods of directly constraining the model output or further training the model on the non-toxic corpus fail to achieve a…

Computation and Language · Computer Science 2024-10-14 Zecheng Tang , Keyan Zhou , Juntao Li , Yuyang Ding , Pinzheng Wang , Bowen Yan , Rejie Hua , Min Zhang

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 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

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 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

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

Computation and Language · Computer Science 2025-10-24 Agam Goyal , Vedant Rathi , William Yeh , Yian Wang , Yuen Chen , Hari Sundaram

This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive…

Computation and Language · Computer Science 2024-05-29 Mengru Wang , Ningyu Zhang , Ziwen Xu , Zekun Xi , Shumin Deng , Yunzhi Yao , Qishen Zhang , Linyi Yang , Jindong Wang , Huajun Chen

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 (LLMs) are increasingly popular but are also prone to generating bias, toxic or harmful language, which can have detrimental effects on individuals and communities. Although most efforts is put to assess and mitigate…

Computation and Language · Computer Science 2024-06-26 Caroline Brun , Vassilina Nikoulina

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) 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 demonstrated remarkable capabilities in performing complex cognitive tasks. However, their complexity and lack of transparency have raised several trustworthiness concerns, including the propagation of…

Machine Learning · Computer Science 2023-11-07 Satyapriya Krishna

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