English
Related papers

Related papers: Towards Safer Pretraining: Analyzing and Filtering…

200 papers

The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. This includes both base models, which are pre-trained on extensive datasets without alignment, and aligned models,…

Computation and Language · Computer Science 2024-04-17 Xiao Wang , Tianze Chen , Xianjun Yang , Qi Zhang , Xun Zhao , Dahua Lin

Caution: this paper may include material that could be offensive or distressing. The advent of Large Language Models (LLMs) necessitates the development of training approaches that mitigate the generation of unethical language and aptly…

Computation and Language · Computer Science 2023-12-01 Sungjoo Byun , Dongjun Jang , Hyemi Jo , Hyopil Shin

Pre-training, which utilizes extensive and varied datasets, is a critical factor in the success of Large Language Models (LLMs) across numerous applications. However, the detailed makeup of these datasets is often not disclosed, leading to…

Cryptography and Security · Computer Science 2024-01-02 Haodong Li , Gelei Deng , Yi Liu , Kailong Wang , Yuekang Li , Tianwei Zhang , Yang Liu , Guoai Xu , Guosheng Xu , Haoyu Wang

The rapid growth of social media platforms has raised significant concerns regarding online content toxicity. When Large Language Models (LLMs) are used for toxicity detection, two key challenges emerge: 1) the absence of domain-specific…

Computation and Language · Computer Science 2025-06-03 Yibo Zhao , Jiapeng Zhu , Can Xu , Yao Liu , Xiang Li

Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be deemed harmful.Efforts to mitigate this risk include…

Computation and Language · Computer Science 2024-08-20 Kexin Chen , Yi Liu , Dongxia Wang , Jiaying Chen , Wenhai Wang

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not…

Computation and Language · Computer Science 2024-01-25 Hongzhan Lin , Ziyang Luo , Wei Gao , Jing Ma , Bo Wang , Ruichao Yang

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

Cryptography and Security · Computer Science 2025-11-26 Benji Peng , Keyu Chen , Ming Li , Pohsun Feng , Ziqian Bi , Junyu Liu , Xinyuan Song , Qian Niu

In an effort to mitigate the harms of large language models (LLMs), learning from human feedback (LHF) has been used to steer LLMs towards outputs that are intended to be both less harmful and more helpful. Despite the widespread adoption…

Computation and Language · Computer Science 2025-06-05 Khaoula Chehbouni , Jonathan Colaço Carr , Yash More , Jackie CK Cheung , Golnoosh Farnadi

Large language models (LLMs) sometimes exhibit dangerous unintended behaviors. Finding and fixing these is challenging because the attack surface is massive -- it is not tractable to exhaustively search for all possible inputs that may…

Machine Learning · Computer Science 2024-07-10 Adriano Hernandez

The potential of large language models (LLMs) to generate harmful content poses a significant safety risk for data management, as LLMs are increasingly being used as engines for data generation. To assess this risk, numerous harmfulness…

Computation and Language · Computer Science 2026-03-19 Langqi Yang , Tianhang Zheng , Yixuan Chen , Kedong Xiu , Hao Zhou , Wangze Ni , Lei Chen , Zhan Qin , Kui Ren

Large Language Models (LLMs) are central to a multitude of applications but struggle with significant risks, notably in generating harmful content and biases. Drawing an analogy to the human psyche's conflict between evolutionary survival…

Computation and Language · Computer Science 2023-11-16 Zi Yin , Wei Ding , Jia Liu

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

High-quality textual training data is essential for the success of multimodal data processing tasks, yet outputs from image captioning models like BLIP and GIT often contain errors and anomalies that are difficult to rectify using…

Computation and Language · Computer Science 2025-02-25 Elyas Meguellati , Nardiena Pratama , Shazia Sadiq , Gianluca Demartini

This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in,…

Computation and Language · Computer Science 2025-09-04 Taiming Lu , Philipp Koehn

WARNING: This paper contains examples of offensive materials. To address the proliferation of toxic content on social media, we introduce SMARTER, we introduce SMARTER, a data-efficient two-stage framework for explainable content moderation…

Computation and Language · Computer Science 2026-04-23 Huy Nghiem , Advik Sachdeva , Hal Daumé

This paper embarks on an exploration into the Large Language Model (LLM) datasets, which play a crucial role in the remarkable advancements of LLMs. The datasets serve as the foundational infrastructure analogous to a root system that…

Computation and Language · Computer Science 2024-02-29 Yang Liu , Jiahuan Cao , Chongyu Liu , Kai Ding , Lianwen Jin

While the widespread deployment of Large Language Models (LLMs) holds great potential for society, their vulnerabilities to adversarial manipulation and exploitation can pose serious safety, security, and ethical risks. As new threats…

Cryptography and Security · Computer Science 2025-09-29 Charankumar Akiri , Harrison Simpson , Kshitiz Aryal , Aarav Khanna , Maanak Gupta

Detecting toxic language including sexism, harassment and abusive behaviour, remains a critical challenge, particularly in its subtle and context-dependent forms. Existing approaches largely focus on isolated message-level classification,…

Toxic language includes content that is offensive, abusive, or that promotes harm. Progress in preventing toxic output from large language models (LLMs) is hampered by inconsistent definitions of toxicity. We introduce TRuST, a large-scale…

Computation and Language · Computer Science 2026-01-07 Berk Atil , Namrata Sureddy , Rebecca J. Passonneau

Large language models (LLMs), such as ChatGPT, have rapidly penetrated into people's work and daily lives over the past few years, due to their extraordinary conversational skills and intelligence. ChatGPT has become the fastest-growing…

Computation and Language · Computer Science 2024-09-04 Wenxuan Wang