English
Related papers

Related papers: Attention Shift: Steering AI Away from Unsafe Cont…

200 papers

In recent years, generative AI (GenAI), like large language models and text-to-image models, has received significant attention across various domains. However, ensuring the responsible generation of content by these models is crucial for…

Computers and Society · Computer Science 2024-09-04 Jindong Gu

Societal cognitive overload, driven by the deluge of information and complexity in the AI age, poses a critical challenge to human well-being and societal resilience. This paper argues that mitigating cognitive overload is not only…

Computers and Society · Computer Science 2025-04-29 Salem Lahlou

Robust content moderation classifiers are essential for the safety of Generative AI systems. In this task, differences between safe and unsafe inputs are often extremely subtle, making it difficult for classifiers (and indeed, even humans)…

Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environment and intensified efforts in searching…

Large-scale self-supervised models have recently revolutionized our ability to perform a variety of tasks within the vision and language domains. However, using such models for autonomous systems is challenging because of safety…

Robotics · Computer Science 2023-03-09 Yue Meng , Sai Vemprala , Rogerio Bonatti , Chuchu Fan , Ashish Kapoor

With the rapid uptake of generative AI, investigating human perceptions of generated responses has become crucial. A major challenge is their `aptitude' for hallucinating and generating harmful contents. Despite major efforts for…

This paper examines refusal behavior in generative AI systems through a governance lens. Drawing on historical frameworks of censorship and contemporary design logics, it argues that refusal is not a neutral safeguard but a site of power,…

Computers and Society · Computer Science 2026-02-03 Kariema El Touny

Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on…

Computer Vision and Pattern Recognition · Computer Science 2023-04-27 Patrick Schramowski , Manuel Brack , Björn Deiseroth , Kristian Kersting

AI safety via debate and reinforcement learning from AI feedback (RLAIF) are both proposed methods for scalable oversight of advanced AI systems, yet no formal framework relates them or characterizes when debate offers an advantage. We…

Machine Learning · Computer Science 2026-03-06 Robin Young

The rapid advancement of large language models (LLMs) has driven their adoption across diverse domains, yet their ability to generate harmful content poses significant safety challenges. While extensive research has focused on mitigating…

Artificial Intelligence · Computer Science 2025-08-29 Yuanzhe Shen , Zisu Huang , Zhengkang Guo , Yide Liu , Guanxu Chen , Ruicheng Yin , Xiaoqing Zheng , Xuanjing Huang

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

Computation and Language · Computer Science 2024-02-20 Zizhong Li , Haopeng Zhang , Jiawei Zhang

The challenge of separating AI-generated text from human-authored content is becoming more urgent as generative AI technologies like ChatGPT become more widely available. In this work, we address this issue by looking at both the detection…

Generative models are widely used for unsupervised learning with various applications, including data compression and signal restoration. Training methods for such systems focus on the generality of the network given limited amount of…

Computer Vision and Pattern Recognition · Computer Science 2017-08-31 Asim Munawar , Phongtharin Vinayavekhin , Giovanni De Magistris

With the rapid development of AI-generated content (AIGC), the creation of high-quality AI-generated videos has become faster and easier, resulting in the Internet being flooded with all kinds of video content. However, the impact of these…

Information Retrieval · Computer Science 2025-07-30 Haowen Gao , Liang Pang , Shicheng Xu , Leigang Qu , Tat-Seng Chua , Huawei Shen , Xueqi Cheng

As generative AI tools like ChatGPT enter classrooms, workplaces and everyday thinking, writing is at risk of becoming a formality -- outsourced, automated and stripped of its cognitive value. But writing is not just output; it is how we…

Computation and Language · Computer Science 2026-03-27 Maria Marina , Alexander Panchenko , Vasily Konovalov

The widespread adoption of ChatGPT has raised concerns about its misuse, highlighting the need for robust detection of AI-generated text. Current word-level detectors are vulnerable to paraphrasing or simple prompts (PSP), suffer from…

Computation and Language · Computer Science 2025-09-24 Mo Mu , Dianqiao Lei , Chang Li

Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can be roughly categorized as finetuning-based and…

Computation and Language · Computer Science 2023-10-17 Chak Tou Leong , Yi Cheng , Jiashuo Wang , Jian Wang , Wenjie Li

Perceptual capabilities of artificial systems have come a long way since the advent of deep learning. These methods have proven to be effective, however they are not as efficient as their biological counterparts. Visual attention is a set…

Machine Learning · Computer Science 2018-11-09 Jarryd Son , Amit Mishra

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

Cryptography and Security · Computer Science 2025-07-18 Yi Nian , Shenzhe Zhu , Yuehan Qin , Li Li , Ziyi Wang , Chaowei Xiao , Yue Zhao

Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A…

Artificial Intelligence · Computer Science 2026-05-12 Xiangkun Sun , Lingkai Kong , Aoqi Zhang , Liang Zeng , Tonghan Wang