相关论文: Extracting Visual Facts from Intermediate Layers f…

The emergence of LLMs, like ChatGPT and Gemini, has marked the modern era of artificial intelligence applications characterized by high-impact applications generating text, images, and videos. However, these models usually ensue with one…

Multimodal Large Language Models (MLLMs) have made significant progress in bridging the gap between visual and language modalities. However, hallucinations in MLLMs, where the generated text does not align with image content, continue to be…

Large Language Models have demonstrated remarkable capabilities across diverse tasks, yet they frequently generate hallucinations outputs that are fluent but factually incorrect or unsupported. We propose Counterfactual Probing, a novel…

Despite the many advances of Large Language Models (LLMs) and their unprecedented rapid evolution, their impact and integration into every facet of our daily lives is limited due to various reasons. One critical factor hindering their…

Diffusion large language models generate text through multi-step denoising, where hallucination signals may emerge throughout the trajectory rather than only in the final output. Existing detectors mainly rely on output uncertainty or…

Though advanced in understanding visual information with human languages, Large Vision-Language Models (LVLMs) still suffer from multimodal hallucinations. A natural concern is that during multimodal interaction, the generated…

Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. However, ``hallucination'', or more specifically, the misalignment between…

Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However, most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs,…

Most Video-Large Language Models (Video-LLMs) adopt an encoder-decoder framework, where a vision encoder extracts frame-wise features for processing by a language model. However, this approach incurs high computational costs, introduces…

While Large Language Models have transformed how we interact with AI systems, they suffer from a critical flaw: they confidently generate false information that sounds entirely plausible. This hallucination problem has become a major…

Language models (LMs) hallucinate. We inquire: Can we detect and mitigate hallucinations before they happen? This work answers this research question in the positive, by showing that the internal representations of LMs provide rich signals…

Recently, Multimodal Large Language Models (MLLMs) have made significant progress in the video comprehension field. Despite remarkable content reasoning and instruction following capabilities they demonstrated, the hallucination problem of…

Vision-language models (VLMs) frequently produce hallucinations in the form of descriptions of objects, attributes, or relations that do not exist in the image due to over-reliance on language priors and imprecise cross-modal grounding. We…

The advancement of Multimodal Large Language Models (MLLMs) has greatly accelerated the development of applications in understanding integrated texts and images. Recent works leverage image-caption datasets to train MLLMs, achieving…

Inspired by the superior language abilities of large language models (LLM), large vision-language models (LVLM) have been recently explored by integrating powerful LLMs for improving the performance on complex multimodal tasks. Despite the…

Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal tasks, but remain susceptible to hallucinations, where generated text deviates from the underlying visual content. Existing hallucination detection methods…

Hallucination is often regarded as a major impediment for using large language models (LLMs), especially for knowledge-intensive tasks. Even when the training corpus consists solely of true statements, language models still generate…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision understanding, reasoning, and interaction. However, the inference computation and memory increase progressively with the generation of output tokens during…

Given the higher information load processed by large vision-language models (LVLMs) compared to single-modal LLMs, detecting LVLM hallucinations requires more human and time expense, and thus rise a wider safety concerns. In this paper, we…

State-of-the-art language models (LMs) sometimes generate non-factual hallucinations that misalign with world knowledge. To explore the mechanistic causes of these hallucinations, we create diagnostic datasets with subject-relation queries…