English
Related papers

Related papers: OVERT: A Benchmark for Over-Refusal Evaluation on …

200 papers

Large language models demonstrate powerful capabilities across various natural language processing tasks, yet they also harbor safety vulnerabilities. To enhance LLM safety, various jailbreak defense methods have been proposed to guard…

Cryptography and Security · Computer Science 2025-11-25 Junbo Zhang , Ran Chen , Qianli Zhou , Xinyang Deng , Wen Jiang

Text-to-image (T2I) models achieve high-fidelity generation through extensive training on large datasets. However, these models may unintentionally pick up undesirable biases of their training data, such as over-representation of particular…

Computer Vision and Pattern Recognition · Computer Science 2024-07-01 Shufan Li , Harkanwar Singh , Aditya Grover

Recent advances in text-to-image generative models have raised concerns about their potential to produce harmful content when provided with malicious input text prompts. To address this issue, two main approaches have emerged: (1)…

Machine Learning · Computer Science 2025-11-13 Jiwoo Shin , Byeonghu Na , Mina Kang , Wonhyeok Choi , Il-Chul Moon

Accurate interpretation and visualization of human instructions are crucial for text-to-image (T2I) synthesis. However, current models struggle to capture semantic variations from word order changes, and existing evaluations, relying on…

Computation and Language · Computer Science 2025-04-18 Xiangru Zhu , Penglei Sun , Yaoxian Song , Yanghua Xiao , Zhixu Li , Chengyu Wang , Jun Huang , Bei Yang , Xiaoxiao Xu

Despite remarkable advancements, current Text-to-Image (T2I) models struggle with complex, long-form textual instructions, frequently failing to accurately render intricate details, spatial relationships, or specific constraints. This…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Xiaochuan Lin , Xiangyong Chen , Xuan Li , Yichen Su

Text-to-image models often struggle to generate images that precisely match textual prompts. Prior research has extensively studied the evaluation of image-text alignment in text-to-image generation. However, existing evaluations primarily…

Computation and Language · Computer Science 2025-06-11 Huixuan Zhang , Xiaojun Wan

Most existing evaluations of text-to-motion generation focus on in-distribution textual inputs and a limited set of evaluation criteria, which restricts their ability to systematically assess model generalization and motion generation…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Bin Yang , Rong Ou , Weisheng Xu , Jiaqi Xiong , Xintao Li , Taowen Wang , Luyu Zhu , Xu Jiang , Jing Tan , Renjing Xu

Bias in text-to-image (T2I) models can propagate unfair social representations and may be used to aggressively market ideas or push controversial agendas. Existing T2I model bias evaluation methods only focus on social biases. We look…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Jordan Vice , Naveed Akhtar , Richard Hartley , Ajmal Mian

Text-to-Image (T2I) generation models have been widely adopted across various industries, yet are criticized for frequently exhibiting societal stereotypes. While a growing body of research has emerged to evaluate and mitigate these biases,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Megan Smith , Venkatesh Thirugnana Sambandham , Florian Richter , Laura Crompton , Matthias Uhl , Torsten Schön

Text-to-image (T2I) models, though exhibiting remarkable creativity in image generation, can be exploited to produce unsafe images. Existing safety measures, e.g., content moderation or model alignment, fail in the presence of white-box…

Cryptography and Security · Computer Science 2025-10-21 Xinfeng Li , Shengyuan Pang , Jialin Wu , Jiangyi Deng , Huanlong Zhong , Yanjiao Chen , Jie Zhang , Wenyuan Xu

Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as…

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Artificial Intelligence · Computer Science 2026-02-20 Arnold Cartagena , Ariane Teixeira

Novel research aimed at text-to-image (T2I) generative AI safety often relies on publicly available datasets for training and evaluation, making the quality and composition of these datasets crucial. This paper presents a comprehensive…

Computation and Language · Computer Science 2025-03-04 Rakeen Rouf , Trupti Bavalatti , Osama Ahmed , Dhaval Potdar , Faraz Jawed

As text-to-image (T2I) models advance and gain widespread adoption, their associated safety concerns are becoming increasingly critical. Malicious users exploit these models to generate Not-Safe-for-Work (NSFW) images using harmful or…

Cryptography and Security · Computer Science 2025-12-10 Yiming Wang , Jiahao Chen , Qingming Li , Tong Zhang , Rui Zeng , Xing Yang , Shouling Ji

Text-to-image (T2I) customization aims to create images that embody specific visual concepts delineated in textual descriptions. However, existing works still face a main challenge, concept overfitting. To tackle this challenge, we first…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Weili Zeng , Yichao Yan , Qi Zhu , Zhuo Chen , Pengzhi Chu , Weiming Zhao , Xiaokang Yang

Text-to-image (T2I) models have become increasingly capable of generating high-quality images. Yet, enforcing the explicit absence of a specified object or attribute remains a fundamentally challenging problem. Existing approaches,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jungmin Ko , Jungwon Park , Jimyeong Kim , Changin Choi , Wonseok Lee , Wonjong Rhee

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem…

Artificial Intelligence · Computer Science 2026-03-13 Zhiyu Xue , Zimo Qi , Guangliang Liu , Bocheng Chen , Ramtin Pedarsani

Recent advances in text-to-video (T2V) technology, as demonstrated by models such as Runway Gen-3, Pika, Sora, and Kling, have significantly broadened the applicability and popularity of the technology. This progress has created a growing…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Zelu Qi , Ping Shi , Shuqi Wang , Chaoyang Zhang , Fei Zhao , Zefeng Ying , Da Pan , Xi Yang , Zheqi He , Teng Dai

Text-to-image (T2I) systems increasingly rely on upstream prompters, either humans or multimodal large language models (MLLMs), to translate user intent into detailed prompts. Yet current benchmarks fix the prompt and only evaluate T2I…

Artificial Intelligence · Computer Science 2026-05-22 Hanjun Luo , Zhimu Huang , Sylvia Chung , Yiran Wang , Yingbin Jin , Jialin Li , Jiang Li , Xinfeng Li , Hanan Salam

Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior…

Multimedia · Computer Science 2026-03-24 Luca Cazzaniga