mlsanityData to 14 Oct 2026

Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models

arXiv 2608.16805 ↗First posted 17 Aug 2026cs.CV cs.AIcited by 1

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic visual-question-answering accuracy marks the response as wrong, while object-hallucination metrics may regard both the object and attribute as image-supported; neither reveals the transfer. This study formalizes this blind spot as Dense Same-Class Attribute Misbinding (DSCAM) and presents InstaBind-Lite, a controlled benchmark that makes it directly measurable. Its 524 images contain 529 curated groups of 3-6 same-class entities, 1773 boxed instances, ordered neighbors, distinguishable color-like attributes, and four complementary question levels, yielding 9580 deterministically evaluated questions. Unlike existing protocols, source-instance annotations separate unsupported generation and recognition failure from an attribute copied from another visible entity. Binding-specific metrics further quantify transfer frequency, adjacency, ordinal distance, and intervention effects. Across five open-source and two commercial/API models, the open-source systems average 19.84% Misbinding Rate and the API systems 7.55%; these errors are hidden by aggregate accuracy. Among identifiable transfers, 80.70% and 81.51%, respectively, originate from adjacent instances. Localization and instance-first interventions help selected models but are not universal remedies. InstaBind-Lite therefore turns previously undifferentiated wrong answers into source-identifiable failure categories and tests a reliability dimension that conventional benchmarks cannot determine: whether a model knows not only what is visible, but which instance owns each attribute.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 38 of its 45 references that are in the map. First posted on arXiv 17 Aug 2026.

Builds on

38 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Investigating Mechanisms for In-Context Vision Language Binding28 May
  2. 2022Flamingo: a Visual Language Model for Few-Shot Learning29 Apr
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation28 Jan

Other references · 35

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  7. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  8. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  9. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  10. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
  11. 2015VQA: Visual Question Answeringcited by 2,506
  12. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
23 more
  1. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  2. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  3. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  4. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  5. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,362
  6. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  7. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  8. 2016Modeling Context in Referring Expressionscited by 1,063
  9. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  10. 2018Object Hallucination in Image Captioningcited by 669
  11. 2022When and why vision-language models behave like bags-of-words, and what to do about it?cited by 610
  12. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 583
  13. 2022Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionalitycited by 529
  14. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 478
  15. 2018MAttNet: Modular Attention Network for Referring Expression Comprehensioncited by 431
  16. 2015Visual7W: Grounded Question Answering in Imagescited by 318
  17. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluationcited by 300
  18. 2023Detecting and Preventing Hallucinations in Large Vision Language Modelscited by 256
  19. 2023SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionalitycited by 243
  20. 2022CREPE: Can Vision-Language Foundation Models Reason Compositionally?cited by 181
  21. 2021Learning to Predict Visual Attributes in the Wildcited by 96
  22. 2026MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generationcited by 4
  23. 2026The Dual Mechanisms of Spatial Variable Binding in Vision-Language Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Whose record is this? Diagnosing and authorizing record use in personalized multimodal modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark
  2. 2024MM-R3: On (In-)Consistency of Vision-Language Models (VLMs)
  3. 2024Evaluating Attribute Comprehension in Large Vision-Language Models
  4. 2026Benchmarking Deflection and Hallucination in Large Vision-Language Models
  5. 2024TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
  6. 2026Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models
  7. 2024UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models
  8. 2025Test-Time Consistency in Vision Language Models