Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
Despite the significant success of Large Vision-Language models(LVLMs), these models still suffer hallucinations when describing images, generating answers that include non-existent objects. It is reported that these models tend to over-focus on certain irrelevant image tokens that do not contain critical information for answering the question and distort the output. To address this, we propose an Instruction-Aligned Visual Attention(IAVA) approach, which identifies irrelevant tokens by comparing changes in attention weights under two different instructions. By applying contrastive decoding, we dynamically adjust the logits generated from original image tokens and irrelevant image tokens, reducing the model's over-attention to irrelevant information. The experimental results demonstrate that IAVA consistently outperforms existing decoding techniques on benchmarks such as MME, POPE, and TextVQA in mitigating object hallucinations. Our IAVA approach is available online at https://github.com/Lee-lab558/IAVA.
Code (1)
Tasks
MMETextVQAMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
Large vision-language models (LVLMs) have shown promising performance on a variety of vision-language tasks. However, they remain susceptible to hallucinations, generating outputs misaligned with visual content or instru…
Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement
Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinations, generating text that contradicts the visual input. Existing res…
Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
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…
HallucinationImage DescriptionQuestion AnsweringVisual Question AnsweringASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Multimodal Large Language Model (MLLM) often suffer from hallucinations. They over-rely on partial cues and generate incorrect responses. Recently, methods like Visual Contrastive Decoding (VCD) and Instruction Contrasti…
HallucinationLanguage ModelingLanguage ModellingLarge Language Model+2HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks. However, the hallucinati…
AttributecounterfactualHallucinationHallucination Evaluation+1