# Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation

arXiv: https://arxiv.org/abs/2604.10071 · HTML: https://mlsanity.com/paper/2604.10071/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)
- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)

## Builds on (most cited first, 29 of 29)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation](https://mlsanity.com/paper/2311.17911/) (2023)
- [Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding](https://mlsanity.com/paper/2403.18715/) (2024)
- [MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation](https://mlsanity.com/paper/2410.11779/) (2024)
- [Look-Back: Implicit Visual Re-focusing in MLLM Reasoning](https://mlsanity.com/paper/2507.03019/) (2025)
- [Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis](https://mlsanity.com/paper/2412.03665/) (2024)
- [Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration](https://mlsanity.com/paper/2502.01969/) (2025)
- [Surveying the MLLM Landscape: A Meta-Review of Current Surveys](https://mlsanity.com/paper/2409.18991/) (2024)
- [Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs](https://mlsanity.com/paper/2503.07772/) (2025)
- [VideoEraser: Concept Erasure in Text-to-Video Diffusion Models](https://mlsanity.com/paper/2508.15314/) (2025)
- [Breaking the Memory Wall for Heterogeneous Federated Learning via Progressive Training](https://mlsanity.com/paper/2404.13349/) (2024)
- [Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning](https://mlsanity.com/paper/2412.11124/) (2024)
- [Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?](https://mlsanity.com/paper/2512.21871/) (2025)
- [MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning](https://mlsanity.com/paper/2411.03314/) (2024)
- [CopyrightMeter: Revisiting Copyright Protection in Text-to-image Models](https://mlsanity.com/paper/2411.13144/) (2024)
- [Elastic Mixture of Rank-Wise Experts for Knowledge Reuse in Federated Fine-Tuning](https://mlsanity.com/paper/2512.00902/) (2025)
- [TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings](https://mlsanity.com/paper/2603.04772/) (2026)
- [Memory-Efficient Federated Fine-Tuning of Large Language Models via Layer Pruning](https://mlsanity.com/paper/2508.17209/) (2025)
- [FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks](https://mlsanity.com/paper/2601.22485/) (2026)
- [Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge](https://mlsanity.com/paper/2604.06819/) (2026)
- ["I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?](https://mlsanity.com/paper/2604.05930/) (2026)

## Built on by (most cited first, 1 of 1)

- [StreamFlow: Dynamic Memory Flows for Streaming Video Understanding](https://mlsanity.com/paper/2608.10949/) (2026)

## Abstract (arXiv)

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.