相关论文: Mitigating Diffusion Model Hallucinations with Dyn…

Large language models (LLMs) often suffer from hallucination, generating factually incorrect or ungrounded content, which limits their reliability in high-stakes applications. A key factor contributing to hallucination is the use of hard…

We fine-tuned a foundational stable diffusion model using X-ray scattering images and their corresponding descriptions to generate new scientific images from given prompts. However, some of the generated images exhibit significant…

Generative models are prone to hallucinations: plausible but incorrect structures absent in the ground truth. This issue is problematic in image restoration for safety-critical domains such as medical imaging, industrial inspection, and…

Large language models (LLMs) have demonstrated exceptional proficiency in language understanding. However, when LLMs align their outputs with deceptive and/or misleading prompts, the generated responses could deviate from the de facto…

Diffusion models have emerged as a formidable tool for training-free conditional generation.However, a key hurdle in inference-time guidance techniques is the need for compute-heavy backpropagation through the diffusion network for…

Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. Such information is coined as guidance. For example, in text-to-image synthesis, text…

Large Vision-Language Models have demonstrated exceptional performance in multimodal reasoning and complex scene understanding. However, these models still face significant hallucination issues, where outputs contradict visual facts. Recent…

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks but still struggle with fine-grained visual differences, leading to hallucinations or missed semantic shifts. We attribute this to…

We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastrophic forgetting by randomly sampling rehearsal examples from…

Guided diffusion is a technique for conditioning the output of a diffusion model at sampling time without retraining the network for each specific task. One drawback of diffusion models, however, is their slow sampling process. Recent…

To address hallucination issues in large language models (LLMs), this paper proposes a method for mitigating prompt-induced hallucinations. Building on a knowledge distillation chain-style model, we introduce a code module to guide…

Large Language Models have rapidly advanced in their ability to interpret and generate natural language. In enterprise settings, they are frequently augmented with closed-source domain knowledge to deliver more contextually informed…

Text-to-image generation models have achieved remarkable capabilities in synthesizing images, but often struggle to provide fine-grained control over the output. Existing guidance approaches, such as segmentation maps and depth maps,…

Recently, there has been an explosion of large language models created through fine-tuning with data from larger models. These small models able to produce outputs that appear qualitatively similar to significantly larger models. However,…

Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to…

Diffusion Models are a potent class of generative models capable of producing high-quality images. However, they often inadvertently favor certain data attributes, undermining the diversity of generated images. This issue is starkly…

Deep learning model effectiveness in classification tasks is often challenged by the quality and quantity of training data whenever they are affected by strong spurious correlations between specific attributes and target labels. This…

Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like…

Data-to-Text Generation (DTG) is a subfield of Natural Language Generation aiming at transcribing structured data in natural language descriptions. The field has been recently boosted by the use of neural-based generators which exhibit on…

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems…