mlsanityData to 14 Oct 2026

RelCheck: Dual-Evidence Spatial Grounding for VLM Hallucination Correction

arXiv 2609.27890 ↗First posted 21 Aug 2026cs.CV cs.AIcited by 0

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

Abstract (arXiv)

Multimodal large language models (MLLMs) fre- quently generate text that is inconsistent with the input image. While object- and attribute-level hallucinations have received considerable attention, relational hallucinations (incorrect de- scriptions of spatial or interactive relationships between objects) remain largely unaddressed by existing post-hoc correction methods. We present RelCheck, a training-free post-hoc correction pipeline that augments object-level visual grounding with dual relational evidence: learned scene-graph triples from RelTR and deterministic spatial predicates from bounding-box geometry. These combine with a Woodpecker-style object claim layer to form a three-layer visual knowledge base, which a language model corrector uses to rewrite hallucinated text. Evaluated on LLaVA v1 13B, RelCheck achieves a total MME hallucination score of 630.0 versus 585.0 for a Woodpecker-style baseline, with the largest gain on the position subtask (+31.7 points, accuracy+ improving from 0.367 to 0.600). A four-configuration ablation confirms that both relational layers contribute independently (McNemar p = 0.025). These results show that structured relational evidence meaningfully improves post-hoc hallucination correction on the spatial reasoning subtasks where current MLLMs are most deficient.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 22 of its 22 references that are in the map. First posted on arXiv 21 Aug 2026.

Builds on

22 of 22 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation29 Nov
  2. 2023Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision13 Nov
  3. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Models24 Oct
  4. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Models1 Oct
  5. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun
  6. 2023Evaluating Object Hallucination in Large Vision-Language Models17 May
  7. 2022Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training14 Oct

Other references · 15

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2023Visual Instruction Tuningcited by 7,869
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  6. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  7. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  8. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  9. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,040
  10. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 706
  11. 2018Object Hallucination in Image Captioningcited by 669
  12. 2022Visual Spatial Reasoningcited by 293
3 more
  1. 2023What's "up" with vision-language models? Investigating their struggle with spatial reasoningcited by 254
  2. 2022RelTR: Relation Transformer for Scene Graph Generationcited by 96
  3. 2021Zero-shot Fact Verification by Claim Generationcited by 42

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Hallucinations Leave a Grounding Signature:Verifier-Guided Decoding for Selective Object Correction
  2. 2026Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
  3. 2026ReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models
  4. 2026HulluEdit: Single-Pass Evidence-Consistent Subspace Editing for Mitigating Hallucinations in Large Vision-Language Models
  5. 2025Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models
  6. 2026Semantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language Models
  7. 2025Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors
  8. 2024Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations