Metraipolis › archive › dc_85bb1b535482
Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled Analysis — arXiv:2609.31456
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31456
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T03:12:48.547Z
- SHA-256 of the archived text
7e8753e5ab5f575126275c0c9695dfcd1a5140d8a1eb76ab397fa6fc15722da6- Stable URL of this page
https://metraipolis.com/documento/dc_85bb1b535482
How to cite
Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled Analysis — arXiv:2609.31456 — arXiv (en), https://arxiv.org/abs/2609.31456 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85bb1b535482 (Metraipolis archive dc_85bb1b535482, sha256 7e8753e5ab5f575126275c0c9695dfcd1a5140d8a1eb76ab397fa6fc15722da6)
BibTeX
@misc{dc85bb1b535482,
title = {Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled Analysis — arXiv:2609.31456},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31456},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85bb1b535482; sha256 7e8753e5ab5f575126275c0c9695dfcd1a5140d8a1eb76ab397fa6fc15722da6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31456. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language models (VLMs) often struggle with compositional reasoning tasks, but the reasons for this underperformance remain unclear. A common hypothesis is that models struggle to integrate multiple components, leading to training interventions to improve compositional binding. However, this assumption has never been directly quantified. Existing benchmarks evaluate captions only in their composed form, making it impossible to separate the cost of joint reasoning from the cost of recognizing individual components under increasing load. We introduce COMPASS (COMPositional Analysis of SkillS), a controlled evaluation framework designed to isolate and measure the distinct factors underlying compositional failure. By comparing performance on composed captions with their decomposed counterparts , we directly quantify the cost of compositional integration across 87K image-caption pairs. Across multiple VLMs, this gap is real but partial, accounting for only part of the observed degradation. This motivates a finer-grained investigation into what additional factors govern model behavior. We analyze performance at the level of individual skills: object detection, attribute binding, and relation reasoning, using skill-targeted perturbations across 274K image-caption pairs. We find a consistent skill-specific pattern: each skill degrades primarily with the count of its own primitive type (self-load), while cross-load effects are predominantly positive, suggesting that primitives of different types provide useful grounding context. This pattern holds across standard contrastive encoders, explicitly trained compositional reasoning models, and non-contrastive architectures. These findings show that compositional degradation reflects multiple separable factors that cannot be reduced to joint reasoning alone. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.31456 — 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 2026-10-08T02:50:19.107Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).