Tutorials
Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation
arXiv:2604.10071v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities yet continue to suffer from hallucination, where generated
arXiv:2604.10071v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities yet continue to suffer from hallucination, where generated text contradicts visual content. In this paper, we introduce Dual-Anchor Introspective Decoding (DaID), a novel contrastive decoding framework that dynamically calibrates each token generation by mining the model's internal perceptual discrepancies. Specifically, DaID identifies a Spotlight layer to amplify visual factual signals and a Shadow layer to suppress textual inertia. By leveraging visual attention distributions to guide this dual-anchor selection process, our method ensures precise, token-specific adaptation. Experimental results across multiple benchmarks and MLLMs demonstrate that DaID significantly mitigates hallucination while enhancing general reasoning capabilities.
Related
- See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment
- Steering the Verifiability of Multimodal AI Hallucinations
- Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding
- CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
- POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
Source: arXiv cs.CV | 2026-04-14