mlsanityData to 14 Oct 2026

MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs

arXiv 2508.10264 ↗First posted 14 Aug 2025cs.CV cs.AIcited by 9

On the map: LLM reasoning → Hallucination detection and mitigation

also in 1 more
Abstract (arXiv)

Large Vision-Language Models (LVLMs) have shown strong performance across multimodal tasks. However, they often produce hallucinations -- text that is inconsistent with visual input, due to the limited ability to verify information in different regions of the image. To address this, we propose Multi-Region Fusion Decoding (MRFD), a training-free decoding method that improves factual grounding by modeling inter-region consistency. MRFD identifies salient regions using cross-attention, generates initial responses for each, and computes reliability weights based on Jensen-Shannon Divergence (JSD) among the responses. These weights guide a consistency-aware fusion of per-region predictions, using region-aware prompts inspired by Chain-of-Thought reasoning. Experiments across multiple LVLMs and benchmarks show that MRFD significantly reduces hallucinations and improves response factuality without requiring model updates.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 23 of its 50 references that are in the map. First posted on arXiv 14 Aug 2025.

Builds on

23 of 50 references.

References · 23

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  3. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  4. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  5. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  6. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  7. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 819
  8. 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 798
  9. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  10. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 357
  11. 2023Faithful Chain-of-Thought Reasoningcited by 288
  12. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Modelscited by 226
11 more
  1. 2024HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decodingcited by 174
  2. 2023Evaluation and Analysis of Hallucination in Large Vision-Language Modelscited by 99
  3. 2025Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Modelscited by 44
  4. 2025M2IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineeringcited by 35
  5. 2021Consensus Graph Representation Learning for Better Grounded Image Captioningcited by 28
  6. 2025Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainabilitycited by 28
  7. 2025TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configurationcited by 23
  8. 2024Language and Multimodal Models in Sports: A Survey of Datasets and Applicationscited by 10
  9. 2024RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Modelscited by 8
  10. 2024Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?cited by 6
  11. 2024Fun with Flags: Robust Principal Directions via Flag Manifoldscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learningcited by 21
  2. 2026PROGRESSLM: Towards Progress Reasoning in Vision-Language Modelscited by 15
  3. 2025ContextNav: Towards Agentic Multimodal In-Context Learningcited by 10
  4. 2025Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoningcited by 8
  5. 2026What Should a Streaming Video Model Remember?cited by 7
  6. 2026VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAGcited by 6
  7. 2026Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Modelscited by 6
  8. 2025Generalist Scanner Meets Specialist Locator: A Synergistic Coarse-to-Fine Framework for Robust GUI Groundingcited by 4
  9. 2026V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failurecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models
  2. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
  3. 2025Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
  4. 2025Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
  5. 2024IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding
  6. 2024Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning
  7. 2026SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation
  8. 2025When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance