paper-with-me

Papers

SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding

2026-02-10 · Zhaoxu Li, Chenqi Kong, Peijun Bao, Song Xia, Yi Tu, Yi Yu, Xinghao Jiang, Xudong Jiang arxiv

Hallucinations in Large Vision-Language Models (LVLMs) pose significant security and reliability risks in real-world applications. Inspired by the observation that humans are more error-prone when uncertain or hesitant, we investigate how instability in a model 's internal knowledge contributes to LVLM hallucinations. We conduct extensive empirical analyses from three perspectives, namely attention heads, model layers, and decoding tokens, and identify three key hallucination patterns: (i) visual activation drift across attention heads, (ii) pronounced knowledge fluctuations across layers, and (iii) visual focus distraction between neighboring output tokens. Building on these findings, we propose Stability-Aware Knowledge-Enhanced Decoding (SAKED), which introduces a layer-wise Knowledge Stability Score (KSS) to quantify knowledge stability throughout the model. By contrasting the most stability-aware and stability-agnostic layers, SAKED suppresses decoding noise and dynamically leverages the most reliable internal knowledge for faithful token generation. Moreover, SAKED is training-free and can be seamlessly integrated into different architectures. Extensive experiments demonstrate that SAKED achieves state-of-the-art performance for hallucination mitigation on various models, tasks, and benchmarks.

📄 PDF Abstract BibTeX arXiv:2602.09825

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback

2024-04-22 · Wenyi Xiao, Ziwei Huang, Leilei Gan, Wanggui He 외

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 give…

AttributeHallucinationSentence

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation

2026-04-22 · Xingyu Zhu, Junfeng Fang, Shuo Wang, Beier Zhu 외 arxiv

Large Vision-Language Models (LVLMs) exhibit powerful generative capabilities but frequently produce hallucinations that compromise output reliability. Fine-tuning on annotated data devoid of hallucinations offers the mo…

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance

2026-02-01 · Xinrong Chen, Xu Chu, Yingmin Qiu, Hengyuan Zhang 외 arxiv

Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and often produce hallucinations. Hallucinat…

Visual Grounding

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization

2024-11-05 · Yuxi Xie, Guanzhen Li, Xiao Xu, Min-Yen Kan

Large vision-language models (LVLMs) suffer from hallucination, resulting in misalignment between the output textual response and the input visual content. Recent research indicates that the over-reliance on the Large La…

HallucinationLanguage ModelingLanguage ModellingLarge Language Model

SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering

2026-07-05 · Kai Tang, Jinhao You, Bohua Zhang, Yichen Guo 외 arxiv

Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answering. However, they remain susceptible to hallucinations, generating …

Visual Question AnsweringFeature EngineeringImage Captioning