Related papers: Visually Dehallucinative Instruction Generation: K…

Large language models are extensively applied across a wide range of tasks, such as customer support, content creation, educational tutoring, and providing financial guidance. However, a well-known drawback is their predisposition to…

Text-to-image generation has shown remarkable progress with the emergence of diffusion models. However, these models often generate factually inconsistent images, failing to accurately reflect the factual information and common sense…

Narrated ''how-to'' videos have emerged as a promising data source for a wide range of learning problems, from learning visual representations to training robot policies. However, this data is extremely noisy, as the narrations do not…

Large Vision-Language Models (LVLMs) have shown remarkable performance on many visual-language tasks. However, these models still suffer from multimodal hallucination, which means the generation of objects or content that violates the…

Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data,…

An ability to learn about new objects from a small amount of visual data and produce convincing linguistic justification about the presence/absence of certain concepts (that collectively compose the object) in novel scenarios is an…

Image-to-Video (I2V) generation models, which condition video generation on reference images, have shown emerging visual instruction-following capability, allowing certain visual cues in reference images to act as implicit control signals…

In visual question answering (VQA) context, users often pose ambiguous questions to visual language models (VLMs) due to varying expression habits. Existing research addresses such ambiguities primarily by rephrasing questions. These…

Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks. However, the hallucinations inherent in…

With the rapid development of artificial intelligence technology, especially the increasingly widespread application of question-and-answer systems, high-quality question generation has become a key component in supporting the development…

The advent of Vision Language Models (VLM) has allowed researchers to investigate the visual understanding of a neural network using natural language. Beyond object classification and detection, VLMs are capable of visual comprehension and…

Multimodal Large Language Models (MLLMs) have made significant strides by combining visual recognition and language understanding to generate content that is both coherent and contextually accurate. However, MLLMs continue to struggle with…

Current visual question answering (VQA) tasks mainly consider answering human-annotated questions for natural images. However, aside from natural images, abstract diagrams with semantic richness are still understudied in visual…

Large vision-language models (LVLMs) excel at multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. We present DROPOUT DECODING, a novel inference-time approach that…

Large Vision-Language Models (LVLMs) bridge the gap between visual and linguistic modalities, demonstrating strong potential across a variety of domains. However, despite significant progress, LVLMs still suffer from severe hallucination…

Visual question answering (VQA) is a Multidisciplinary research problem that pursued through practices of natural language processing and computer vision. Visual question answering automatically answers natural language questions according…

Knowledge-to-text generators often struggle to faithfully generate descriptions for the input facts: they may produce hallucinations that contradict the input, or describe facts not present in the input. To reduce hallucinations, we propose…

Despite improvements in performances on different natural language generation tasks, deep neural models are prone to hallucinating facts that are incorrect or nonexistent. Different hypotheses are proposed and examined separately for…

Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectly when the correct answer is absent from its generation-time distribution, and correctly when it is present. We test this assumption by…

Hallucination is a persistent challenge in large language models (LLMs), where even with rigorous quality control, models often generate distorted facts. This paradox, in which error generation continues despite high-quality training data,…