# Attribution Gaps in Zero-Training LLM+OVOD Pipelines: A Fine-Grained Analysis of the CAAP--SNAP Discrepancy

arXiv: https://arxiv.org/abs/2609.32567 · HTML: https://mlsanity.com/paper/2609.32567/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 11 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [TIDE: A General Toolbox for Identifying Object Detection Errors](https://mlsanity.com/paper/2008.08115/) (2020)
- [ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO](https://mlsanity.com/paper/2204.03359/) (2022)
- [LLM-Guided Agentic Object Detection for Open-World Understanding](https://mlsanity.com/paper/2507.10844/) (2025)

## Abstract (arXiv)

LAOD and similar zero-training LLM+open-vocabulary-detector (OVOD) pipelines score two things separately: class-agnostic localization accuracy (CAAP) and semantic naming accuracy (SNAP). The two consistently diverge, and nobody has asked why. This paper asks why, on the full 5,000-image COCO-Val split (27,273 detections) rather than the small subset the original work evaluated on. Object visual complexity turns out not to be the driver -- small and occluded objects are, if anything, localized better than large ones. Vocabulary novelty is: once the LLM's wording falls outside the detector's native category set, localization accuracy falls from 80.9% to 31.6%. That drop is not spread evenly across unfamiliar phrasing, though. Almost all of it comes from cases where the novel wording actually names a different object than the one COCO annotated (true synonyms still score 89.3%; semantically unrelated "noise" labels score 12.0%). A closer look at a further failure subset tells a similar story: 78-88% of what looks like complete localization failure is really the model correctly finding a real object that COCO's non-exhaustive 80-category scheme simply never labeled, not hallucination. Swap the detector backbone (YOLO-World for Grounding DINO) or the LLM (Gemma-3 for Qwen2.5-VL) and both the effect and its rough size hold up, so this looks like a general property of the pipeline family rather than a quirk of one model pairing. The upshot is that a large share of the apparent CAAP--SNAP gap traces back to closed-category annotation limits rather than a real grounding failure, which matters for how we detect hallucination, analyze failure modes, and design evaluation for grounded multimodal systems meant to work in the open world.