mlsanityData to 14 Oct 2026

Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding

arXiv 2512.19070 ↗First posted 22 Dec 2025cs.CV cs.CLcited by 2

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Large Vision-Language Models (LVLMs) bridge the gap between visual and linguistic modalities, demonstrating strong potential across a variety of domains. However, despite significant progress, LVLMs still suffer from severe hallucination issues in object recognition tasks. These models often fail to accurately identify certain objects, leading to text generation that appears fluent but does not correspond to the visual content, which can have serious consequences in real-world applications. Recently, several methods have been proposed to alleviate LVLM hallucinations, but most focus solely on reducing hallucinations in the language modality. To mitigate hallucinations in both the language and visual modalities, we introduce Hallucination Disentangled Decoding (HDD) method that requires no training. HDD enhances the original image by segmenting it and selecting images that augment the original, while also utilizing a blank image to eliminate language prior hallucinations in both the original and segmented images. This design not only reduces the model's dependence on language priors but also enhances its visual performance. (Code: https://github.com/rickeyhhh/Hallucination-Disentangled-Decoding)

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 20 of its 30 references that are in the map. First posted on arXiv 22 Dec 2025.

Builds on

20 of 30 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training9 Mar
  2. 2024CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs19 Nov
  3. 2024Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models4 Aug
  4. 2024Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs31 Jul
  5. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding27 Mar
  6. 2024HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding1 Mar
  7. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation29 Nov
  8. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  9. 2023HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data22 Nov

Other references · 11

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2017Mask R-CNNcited by 7,277
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  7. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  9. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledgecited by 710
  10. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
  11. 2019GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answeringcited by 78

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigationcited by 1
  2. 2026Sparse Visual Thought Circuits in Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors
  2. 2024Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)
  3. 2024Reducing Hallucinations in Vision-Language Models via Latent Space Steering
  4. 2025Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models
  5. 2025ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models
  6. 2025Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors
  7. 2026SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
  8. 2024Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding