Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation

• URL: http://arxiv.org/abs/2603.07048v1
• Date: Sat, 07 Mar 2026 05:57:27 GMT
• Title: Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation
• Abstract summary: Large vision-language models (LVLMs) are prone to hallucinations in multi-image tasks.<n>We propose a structured hallucination mitigation framework involving Cross-Image Attention calibration and Preference Learning.
• Score: 48.06125338526647
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitations in existing attention mechanisms and insufficient cross-image modeling. Inspired by this, we propose a structured hallucination mitigation framework involving Cross-Image Attention calibration and Preference Learning (CAPL). CAPL explicitly enhances inter-image interactions at the architectural level while reinforcing reliance on genuine cross-image evidence during training, thereby improving the model's perception and modeling of cross-image associations. Specifically, we (i) introduce a selectable image token interaction attention mechanism to establish fine-grained cross-image entity alignment and information flow; (ii) design a cross-image modeling-based preference optimization strategy that contrasts reasoning outcomes under full inter-image interaction and those obtained when images are mutually invisible, encouraging the model to ground its predictions in authentic visual evidence and mitigating erroneous inferences driven by textual priors. Experimental results demonstrate that CAPL consistently improves performance across multiple model architectures, achieving stable gains on both multi-image hallucination and general benchmarks. Notably, performance on single-image visual tasks remains stable or slightly improves, indicating strong generalization capability.

Related papers

• S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language Models [8.92478226038086]
  We introduce a learning framework that constructs multi-image preference data across three hierarchical reasoning levels.<n>Our approach maintains strong single-image reasoning performance while simultaneously strengthening multi-image understanding capabilities.
  arXiv  Detail & Related papers  (2026-04-20T17:06:20Z)
• Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation [81.40978077888693]
  Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance.<n>Recent solutions use diffusion models to enhance representations by conditioning image reconstruction on CLIP visual tokens.<n>We integrate contrastive signals into diffusion-based reconstruction to pursue more comprehensive visual representations.
  arXiv  Detail & Related papers  (2026-03-05T04:45:49Z)
• Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching [31.42132290162457]
  We introduce a new framework called IMD (Image feature Matching with a pre-trained Diffusion model) with two parts.<n>Unlike the dominant solutions employing contrastive-learning based foundation models that emphasize global semantics, we integrate the generative-based diffusion models.<n>Our proposed IMD establishes a new state-of-the-art in commonly evaluated benchmarks, and the superior 12% improvement in IMIM indicates our method efficiently mitigates the misalignment.
  arXiv  Detail & Related papers  (2025-07-14T14:28:15Z)
• Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy [53.07517728420411]
  We introduce the first instruction database specifically focused on hallucinations in low-level vision tasks.<n>We propose the Self-Awareness Failure Elimination (SAFEQA) model to improve the perception and comprehension abilities of the model in low-level vision tasks.<n>We conduct comprehensive experiments on low-level vision tasks, with the results demonstrating that our proposed method significantly enhances self-awareness of the model in these tasks and reduces hallucinations.
  arXiv  Detail & Related papers  (2025-03-26T16:05:01Z)
• Multi-Head Attention Driven Dynamic Visual-Semantic Embedding for Enhanced Image-Text Matching [0.8611782340880084]
  This study proposes an innovative visual semantic embedding model, Multi-Headed Consensus-Aware Visual-Semantic Embedding (MH-CVSE)<n>This model introduces a multi-head self-attention mechanism based on the consensus-aware visual semantic embedding model (CVSE) to capture information in multiple subspaces in parallel.<n>In terms of loss function design, the MH-CVSE model adopts a dynamic weight adjustment strategy to dynamically adjust the weight according to the loss value itself.
  arXiv  Detail & Related papers  (2024-12-26T11:46:22Z)
• Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignment [20.902935570581207]
  We introduce a Multimodal Alignment and Reconstruction Network (MARNet) to enhance the model's resistance to visual noise. MARNet includes a cross-modal diffusion reconstruction module for smoothly and stably blending information across different domains. Experiments conducted on two benchmark datasets, Vireo-Food172 and Ingredient-101, demonstrate that MARNet effectively improves the quality of image information extracted by the model.
  arXiv  Detail & Related papers  (2024-07-26T16:30:18Z)
• ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling [11.129453244307369]
  FG-SBIR aims to minimize the distance between sketches and corresponding images in the embedding space.<n>We propose an effective approach to narrow the gap between the two domains.<n>It mainly facilitates unified mutual information sharing both intra- and inter-samples.
  arXiv  Detail & Related papers  (2024-06-17T13:49:12Z)
• Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection [58.228940066769596]
  We introduce a Dual-Image Enhanced CLIP approach, leveraging a joint vision-language scoring system. Our methods process pairs of images, utilizing each as a visual reference for the other, thereby enriching the inference process with visual context. Our approach significantly exploits the potential of vision-language joint anomaly detection and demonstrates comparable performance with current SOTA methods across various datasets.
  arXiv  Detail & Related papers  (2024-05-08T03:13:20Z)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)
• Bridging Synthetic and Real Images: a Transferable and Multiple Consistency aided Fundus Image Enhancement Framework [61.74188977009786]
  We propose an end-to-end optimized teacher-student framework to simultaneously conduct image enhancement and domain adaptation. We also propose a novel multi-stage multi-attention guided enhancement network (MAGE-Net) as the backbones of our teacher and student network.
  arXiv  Detail & Related papers  (2023-02-23T06:16:15Z)

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.