MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing

• URL: http://arxiv.org/abs/2508.01653v1
• Date: Sun, 03 Aug 2025 08:23:31 GMT
• Title: MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
• Authors: Chenxi Li, Yichen Guo, Benfang Qian, Jinhao You, Kai Tang, Yaosong Du, Zonghao Zhang, Xiande Huang,
• Abstract summary: Large Vision-Language Models (LVLMs) have achieved impressive performance in multimodal tasks, but they still suffer from hallucinations.<n>We introduce a novel map-level perspective to mitigate hallucinations in LVLMs, interpreting the hidden states of the model as a 2D semantic map.<n>We propose Map-Level Attention Processing (MAP), a training-free decoding method that effectively leverages factual information through attention-based map-level operations.
• Score: 7.288683073985627
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Vision-Language Models (LVLMs) have achieved impressive performance in multimodal tasks, but they still suffer from hallucinations, i.e., generating content that is grammatically accurate but inconsistent with visual inputs. In this work, we introduce a novel map-level perspective to mitigate hallucinations in LVLMs, interpreting the hidden states of the model as a 2D semantic map. We observe that factual information is widely distributed across this map, extending beyond the localized inter- or intra-layer regions targeted by most existing methods (e.g., contrastive decoding and layer-wise consistency). Building on this insight, we propose Map-Level Attention Processing (MAP), a training-free decoding method that effectively leverages factual information through attention-based map-level operations to improve factual consistency. Specifically, we employ Layer-Wise Criss-Cross Attention to progressively refine token representations at each decoding layer by aggregating tokens from both inter- and intra-layer dimensions. Additionally, a Global-Local Logit Fusion mechanism combines logits obtained before and after global attention to further refine predictions and improve accuracy. Our method consistently improves the truthfulness and performance of LVLMs across benchmarks, such as POPE, MME, and MMHal-Bench, demonstrating the potential of the map-level decoding strategy.

Related papers

• Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos [53.723410664944566]
  We present Perceive Anything Model (PAM), a framework for comprehensive region-level visual understanding in images and videos.<n>Our approach extends the powerful segmentation model SAM 2 by integrating Large Language Models (LLMs), enabling simultaneous object segmentation.<n>A key component, Semantic Perceiver, is introduced to efficiently transform SAM 2's rich visual features into multi-modal tokens.
  arXiv  Detail & Related papers  (2025-06-05T17:51:39Z)
• Rethinking Cell Counting Methods: Decoupling Counting and Localization [20.458912966915843]
  We propose a conceptually simple yet effective decoupled learning scheme for automated cell counting.<n>In contrast to jointly learning counting and density map estimation, we show that decoupling these objectives surprisingly improves results.<n>Our key insight is that decoupled learning alleviates the need to learn counting on high-resolution density maps directly.
  arXiv  Detail & Related papers  (2025-03-18T07:50:03Z)
• Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference [28.24397677839652]
  Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models.<n>How MLLMs process and utilize visual information remains unclear.<n>We propose Hierarchical Modality-Aware Pruning (HiMAP), a plug-and-play inference acceleration method that dynamically prunes image tokens at specific layers, reducing computational costs by approximately 65% without sacrificing performance.
  arXiv  Detail & Related papers  (2025-03-17T12:31:23Z)
• AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding [63.09928907734156]
  AlignVLM is a vision-text alignment method that maps visual features to a weighted average of text embeddings.<n>Our experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods.
  arXiv  Detail & Related papers  (2025-02-03T13:34:51Z)
• ResCLIP: Residual Attention for Training-free Dense Vision-language Inference [27.551367463011008]
  Cross-correlation of self-attention in CLIP's non-final layers also exhibits localization properties. We propose the Residual Cross-correlation Self-attention (RCS) module, which leverages the cross-correlation self-attention from intermediate layers to remold the attention in the final block. The RCS module effectively reorganizes spatial information, unleashing the localization potential within CLIP for dense vision-language inference.
  arXiv  Detail & Related papers  (2024-11-24T14:14:14Z)
• OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Fused Geometric and Semantic Guidance [11.085165252259042]
  OSMLoc is a brain-inspired visual localization approach based on first-person-view images against the OpenStreetMap maps.<n>It integrates semantic and geometric guidance to significantly improve accuracy, robustness, and generalization capability.
  arXiv  Detail & Related papers  (2024-11-13T14:59:00Z)
• Probing Multimodal Large Language Models for Global and Local Semantic Representations [57.25949445963422]
  We study which layers of Multimodal Large Language Models make the most effort to the global image information. In this study, we find that the intermediate layers of models can encode more global semantic information. We find that the topmost layers may excessively focus on local information, leading to a diminished ability to encode global information.
  arXiv  Detail & Related papers  (2024-02-27T08:27:15Z)
• A Self-Training Framework Based on Multi-Scale Attention Fusion for Weakly Supervised Semantic Segmentation [7.36778096476552]
  We propose a self-training method that utilizes fused multi-scale class-aware attention maps. We collect information from attention maps of different scales and obtain multi-scale attention maps. We then apply denoising and reactivation strategies to enhance the potential regions and reduce noisy areas.
  arXiv  Detail & Related papers  (2023-05-10T02:16:12Z)
• BEVBert: Multimodal Map Pre-training for Language-guided Navigation [75.23388288113817]
  We propose a new map-based pre-training paradigm that is spatial-aware for use in vision-and-language navigation (VLN) We build a local metric map to explicitly aggregate incomplete observations and remove duplicates, while modeling navigation dependency in a global topological map. Based on the hybrid map, we devise a pre-training framework to learn a multimodal map representation, which enhances spatial-aware cross-modal reasoning thereby facilitating the language-guided navigation goal.
  arXiv  Detail & Related papers  (2022-12-08T16:27:54Z)
• L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation [67.26984058377435]
  We present L2G, a simple online local-to-global knowledge transfer framework for high-quality object attention mining. Our framework conducts the global network to learn the captured rich object detail knowledge from a global view. Experiments show that our method attains 72.1% and 44.2% mIoU scores on the validation set of PASCAL VOC 2012 and MS COCO 2014.
  arXiv  Detail & Related papers  (2022-04-07T04:31:32Z)
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency [61.40511574314069]
  Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
  arXiv  Detail & Related papers  (2021-06-20T08:20:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.