相关论文: ToViLaG: Your Visual-Language Generative Model is …

The proliferation of Large Language Models (LLMs) in real-world applications poses unprecedented risks of generating harmful, biased, or misleading information to vulnerable populations including LGBTQ+ individuals, single parents, and…

Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However, it is still unclear whether they can recognize various…

Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-level filtering with no mechanistic insight into where toxicity originates internally. We…

Large Language Models (LLMs) have become integral to Software Engineering (SE), increasingly used in development workflows. However, their widespread adoption raises concerns about the presence and propagation of toxic language - harmful or…

Multimodal retrieval-augmented generation (RAG) enhances the visual reasoning capability of vision-language models (VLMs) by dynamically accessing information from external knowledge bases. In this work, we introduce \textit{Poisoned-MRAG},…

While in real life everyone behaves themselves at least to some extent, it is much more difficult to expect people to behave themselves on the internet, because there are few checks or consequences for posting something toxic to others.…

While recent Large Vision-Language Models (LVLMs) have shown remarkable performance in multi-modal tasks, they are prone to generating hallucinatory text responses that do not align with the given visual input, which restricts their…

In this work, we introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for…

There has been an increasing interest in the alignment of large language models (LLMs) with human values. However, the safety issues of their integration with a vision module, or vision language models (VLMs), remain relatively…

Medical reports with substantial information can be naturally complementary to medical images for computer vision tasks, and the modality gap between vision and language can be solved by vision-language matching (VLM). However, current…

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs), but simultaneously exposes a critical vulnerability to knowledge poisoning attacks. Existing attack methods like PoisonedRAG remain detectable due to…

In the realm of vision models, the primary mode of representation is using pixels to rasterize the visual world. Yet this is not always the best or unique way to represent visual content, especially for designers and artists who depict the…

We propose a method to control the attributes of Language Models (LMs) for the text generation task using Causal Average Treatment Effect (ATE) scores and counterfactual augmentation. We explore this method, in the context of LM…

The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource…

Toxicity is a prevalent social behavior that involves the use of hate speech, offensive language, bullying, and abusive speech. While text-based approaches for toxicity detection are common, there is limited research on processing speech…

Effective toxic content detection relies heavily on high-quality and diverse data, which serve as the foundation for robust content moderation models. Synthetic data has become a common approach for training models across various NLP tasks.…

Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly…

To address the risks of encountering inappropriate or harmful content, researchers managed to incorporate several harmful contents datasets with machine learning methods to detect harmful concepts. However, existing harmful datasets are…

Recent advancements in generation models have showcased remarkable capabilities in generating fantastic content. However, most of them are trained on proprietary high-quality data, and some models withhold their parameters and only provide…

Text-to-image generation models have achieved strong performance in culturally homogeneous settings, yet their ability to generate multicultural scenes, where people and landmarks originate from different cultures, remains largely…