Related papers: CHASD: Language Increment-Calibrated Contrastive D…

The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…

Although Large Vision-Language Models (LVLMs) have demonstrated powerful capabilities in interpreting visual information, they frequently produce content that deviates from visual information, leading to object hallucination. To tackle…

This study addresses the problem of hallucinated span detection in the outputs of large language models. It has received less attention than output-level hallucination detection despite its practical importance. Prior work has shown that…

Despite their remarkable capabilities, Large Language Models (LLMs) are prone to generate responses that contradict verifiable facts, i.e., unfaithful hallucination content. Existing efforts generally focus on optimizing model parameters or…

Recent advancements in Large Vision-Language Models (LVLMs) have significantly expanded their utility in tasks like image captioning and visual question answering. However, they still struggle with object hallucination, where models…

Large vision-language models (LVLMs) have achieved remarkable performance on multimodal tasks. However, they still suffer from hallucinations, generating text inconsistent with visual input, posing significant risks in real-world…

Multivariate time series anomaly detection has become increasingly important in real-world applications, where labeled data are often scarce. Many existing approaches rely on unsupervised learning to model normal patterns, but they often…

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled them to effectively integrate vision and language, addressing a variety of downstream tasks. However, despite their significant success, these models still exhibit…

Contradictory multimodal inputs are common in real-world settings, yet existing benchmarks typically assume input consistency and fail to evaluate cross-modal contradiction detection - a fundamental capability for preventing hallucinations…

Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon…

While large language models have transformed how we interact with AI systems, they have a critical weakness: they confidently state false information that sounds entirely plausible. This "hallucination" problem has become a major barrier to…

Generative Vision-Language Models (VLMs) are prone to generate plausible-sounding textual answers that, however, are not always grounded in the input image. We investigate this phenomenon, usually referred to as "hallucination" and show…

Despite their remarkable progress in multimodal understanding tasks, large vision language models (LVLMs) often suffer from "hallucinations", generating texts misaligned with the visual context. Existing methods aimed at reducing…

Diffusion large language models (D-LLMs) have recently emerged as a promising alternative to auto-regressive LLMs (AR-LLMs). However, the hallucination problem in D-LLMs remains underexplored, limiting their reliability in real-world…

Large Vision-Language Models (LVLMs) have achieved impressive progress in multi-modal understanding and generation. However, they still tend to produce hallucinated content that is inconsistent with the visual input, which limits their…

Large Language Models (LLMs) often produce fluent yet factually incorrect statements-a phenomenon known as hallucination-posing serious risks in high-stakes domains. We present Layer-wise Semantic Dynamics (LSD), a geometric framework for…

Vision-Language Models (VLMs) are frequently undermined by object hallucination, generating content that contradicts visual reality, due to an over-reliance on linguistic priors. We introduce Positive-and-Negative Decoding (PND), a…

Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do…

LVLMs achieve remarkable multimodal understanding and generation but remain susceptible to hallucinations. Existing mitigation methods predominantly focus on output-level adjustments, leaving the internal mechanisms that give rise to these…

Recent Large Vision-Language Models (LVLMs) have introduced a new paradigm for understanding and reasoning about image input through textual responses. Although they have achieved remarkable performance across a range of multi-modal tasks,…