Metraipolis › archive › dc_eda2e9f36382
Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models — arXiv:2608.16805
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16805
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:07:33.480Z
- SHA-256 of the archived text
3291205a0250d0088878baa3d4098825a8c6a9effce268b5820acd61b03e3d3b- Stable URL of this page
https://metraipolis.com/documento/dc_eda2e9f36382
How to cite
Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models — arXiv:2608.16805 — arXiv (en), https://arxiv.org/abs/2608.16805 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eda2e9f36382 (Metraipolis archive dc_eda2e9f36382, sha256 3291205a0250d0088878baa3d4098825a8c6a9effce268b5820acd61b03e3d3b)
BibTeX
@misc{dceda2e9f36382,
title = {Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models — arXiv:2608.16805},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16805},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eda2e9f36382; sha256 3291205a0250d0088878baa3d4098825a8c6a9effce268b5820acd61b03e3d3b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16805. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.16805 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:14.159Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).