Related papers: HaloProbe: Bayesian Detection and Mitigation of Ob…
Large Vision-Language Models (LVLMs) are susceptible to hallucinations, where generated responses seem semantically plausible yet exhibit little or no relevance to the input image. Previous studies reveal that this issue primarily stems…
Large vision-language models (LVLMs) have achieved remarkable performance across diverse multimodal tasks, yet they continue to suffer from hallucinations, generating content that is inconsistent with the visual input. Prior work DHCP…
Hallucinations remain a persistent challenge for vision-language models (VLMs), which often describe nonexistent objects or fabricate facts. Existing detection methods typically operate after text generation, making intervention both costly…
Retrieval-Augmented Generation (RAG) models frequently encounter hallucination phenomena when integrating external information with internal parametric knowledge. Empirical studies demonstrate that the disequilibrium between external…
Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal abilities but remain prone to multilingual object hallucination, with a higher likelihood of generating responses inconsistent with the visual input when utilizing…
Multimodal large language models achieve strong performance across diverse tasks but remain prone to hallucinations, where outputs are not grounded in visual inputs. This issue can be attributed to two main biases: text-visual bias, the…
Vision language models (VLMs) perceive the world through a combination of a visual encoder and a large language model (LLM). The visual encoder, pre-trained on large-scale vision-text datasets, provides zero-shot generalization to visual…
Large vision-language models (LVLMs) achieve strong multimodal performance, but still suffer from hallucinations caused by unstable visual grounding and over-reliance on language priors. Existing training-free decoding methods typically…
Hallucinations in large vision-language models (LVLMs) often stem from the model's sensitivity to image tokens during decoding, as evidenced by attention peaks observed when generating both real and hallucinated entities. To address this,…
Large Vision-Language Models (VLMs) often exhibit text inertia, where attention drifts from visual evidence toward linguistic priors, resulting in object hallucinations. Existing decoding strategies intervene only at the output logits and…
Hallucination, or the generation of incorrect or fabricated information, remains a critical challenge in large language models (LLMs), particularly in high-stake domains such as legal question answering (QA). In order to mitigate the…
We study object hallucination in Multimodal Large Language Models (MLLMs) and improve visual contrastive decoding (VCD) by constructing an object-aligned auxiliary view. We leverage object-centric attention in self-supervised Vision…
Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon known as object…
We investigate the internal representations of vision-language models (VLMs) to address hallucinations, a persistent challenge despite advances in model size and training. We project VLMs' internal image representations to their language…
Object hallucination in large vision-language models presents a significant challenge to their safe deployment in real-world applications. Recent works have proposed object-level hallucination scores to estimate the likelihood of object…
With the advent of rich visual representations and pre-trained language models, video captioning has seen continuous improvement over time. Despite the performance improvement, video captioning models are prone to hallucination.…
Hallucinations in Large Language Models (LLMs), defined as the generation of content inconsistent with facts or context, represent a core obstacle to their reliable deployment in critical domains. Current research primarily focuses on…
Aligning large language models (LLMs) to accurately detect hallucinations remains a significant challenge due to the sophisticated nature of hallucinated text. Recognizing that hallucinated samples typically exhibit higher deceptive quality…
Contrastive decoding strategies are widely used to mitigate object hallucinations in multimodal large language models (MLLMs). By reducing over-reliance on language priors, these strategies ensure that generated content remains closely…
Recent advances in large language models (LLMs) have shown promising improvements, often surpassing existing methods across a wide range of downstream tasks in natural language processing. However, these models still face challenges, which…