English
Related papers

Related papers: CMD: a framework for Context-aware Model self-Deto…

200 papers

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

Large Language Models (LLMs) have significantly advanced natural language processing (NLP) tasks but also pose ethical and societal risks due to their propensity to generate harmful content. Existing methods have limitations, including the…

Computation and Language · Computer Science 2025-05-22 Ximing Dong , Dayi Lin , Shaowei Wang , Ahmed E. Hassan

Text detoxification is a textual style transfer (TST) task where a text is paraphrased from a toxic surface form, e.g. featuring rude words, to the neutral register. Recently, text detoxification methods found their applications in various…

Computation and Language · Computer Science 2024-04-03 Daryna Dementieva , Nikolay Babakov , 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

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

Large Language Models (LLMs) and Vision Language Models (VLMs) have recently shown promising capabilities in various scientific domain. In particular, these advances have opened new opportunities in drug discovery, where the ability to…

Artificial Intelligence · Computer Science 2026-05-13 Jueon Park , Wonjune Jang , Jiwoo Lee , Yein Park , Jaewoo Kang

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

Cryptography and Security · Computer Science 2025-08-15 Jinhwa Kim , Ian G. Harris

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

We present Contamination Detection via Context (CoDeC), a practical and accurate method to detect and quantify training data contamination in large language models. CoDeC distinguishes between data memorized during training and data outside…

Computation and Language · Computer Science 2026-05-13 Michał Zawalski , Meriem Boubdir , Klaudia Bałazy , Besmira Nushi , Pablo Ribalta

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

Even with various regulations in place across countries and social media platforms (Government of India, 2021; European Parliament and Council of the European Union, 2022, digital abusive speech remains a significant issue. One potential…

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

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

Computation and Language · Computer Science 2025-12-03 Kecheng Chen , Ziru Liu , Xijia Tao , Hui Liu , Xinyu Fu , Suiyun Zhang , Dandan Tu , Lingpeng Kong , Rui Liu , Haoliang Li

The success of speech-image retrieval relies on establishing an effective alignment between speech and image. Existing methods often model cross-modal interaction through simple cosine similarity of the global feature of each modality,…

Computation and Language · Computer Science 2024-09-12 Lifeng Zhou , Yuke Li , Rui Deng , Yuting Yang , Haoqi Zhu

Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual…

Computation and Language · Computer Science 2024-03-06 Yifu Sun , Haoming Jiang

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

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

Definition modeling is an important task in advanced natural language applications such as understanding and conversation. Since its introduction, it focus on generating one definition for a target word or phrase in a given context, which…

Computation and Language · Computer Science 2023-05-25 Linhan Zhang , Qian Chen , Wen Wang , Yuxin Jiang , Bing Li , Wei Wang , Xin Cao

Knowledge-Editing-based (KE-based) detoxification has emerged as a promising approach for mitigating harmful behaviours in Large Language Models. Existing evaluations, however, largely rely on automatic toxicity classifiers, implicitly…

Computation and Language · Computer Science 2026-02-12 Ming Dong , Shiyi Tang , Ziyan Peng , Guanyi Chen , Tingting He