相关论文: Steering LVLMs via Sparse Autoencoder for Hallucin…

Due to the unidirectional masking mechanism, Decoder-Only models propagate information from left to right. LVLMs (Large Vision-Language Models) follow the same architecture, with visual information gradually integrated into semantic…

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically rely solely on…

The rapidly developing Large Vision Language Models (LVLMs) have shown notable capabilities on a range of multi-modal tasks, but still face the hallucination phenomena where the generated texts do not align with the given contexts,…

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse…

Hallucination remains a key obstacle to the reliable deployment of large language models (LLMs) in real-world question answering tasks. A widely adopted strategy to detect hallucination, known as self-assessment, relies on the model's own…

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 Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to…

Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects…

Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal task reasoning. However, they often generate responses that appear plausible yet do not accurately reflect the visual content, a phenomenon known…

Visual hallucinations in Large Language Models (LLMs), where the model generates responses that are inconsistent with the visual input, pose a significant challenge to their reliability, particularly in contexts where precise and…

Large vision-language models (LVLMs) have demonstrated remarkable multimodal comprehension and reasoning capabilities, but they still suffer from severe object hallucination. Previous studies primarily attribute the flaw to linguistic prior…

Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual information, the choice of visual encoder is pivotal. We…

Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper…

Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in understanding and describing visual content, achieving state-of-the-art performance across various vision-language tasks. However, these models often generate…

Large vision-language models (LVLMs) are now central to healthcare applications such as medical visual question answering and imaging report generation. Yet, these models remain vulnerable to hallucination outputs that appear plausible but…

Spatial relation hallucinations pose a persistent challenge in large vision-language models (LVLMs), leading to generate incorrect predictions about object positions and spatial configurations within an image. To address this issue, we…

Hallucination has been a long-standing and inevitable problem that hinders the application of Large Vision-Language Models (LVLMs) in domains that require high reliability. Various methods focus on improvement depending on data annotations…

Medical vision-language models (VLMs) often hallucinate findings when generating chest X-ray reports: they fabricate findings that are not present in the image, miss important ones, or locate them incorrectly. We mitigate this without…

Large Vision-Language Models (LVLMs) excel in diverse cross-modal tasks. However, object hallucination, where models produce plausible but inaccurate object descriptions, remains a significant challenge. In contrast to previous work…