# MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts

arXiv: https://arxiv.org/abs/2607.18673 · HTML: https://mlsanity.com/paper/2607.18673/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 25 of 25)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles](https://mlsanity.com/paper/2503.17352/) (2025)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2402.14409/) (2024)
- [More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models](https://mlsanity.com/paper/2505.21523/) (2025)
- [Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs](https://mlsanity.com/paper/2410.08145/) (2024)
- [MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs](https://mlsanity.com/paper/2406.17126/) (2024)
- [Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models](https://mlsanity.com/paper/2505.19509/) (2025)
- [BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models](https://mlsanity.com/paper/2407.13442/) (2024)
- [Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs](https://mlsanity.com/paper/2501.19164/) (2025)
- [Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images](https://mlsanity.com/paper/2512.17306/) (2025)
- [LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset](https://mlsanity.com/paper/2503.02910/) (2025)
- [Investigating Tool-Memory Conflicts in Tool-Augmented LLMs](https://mlsanity.com/paper/2601.09760/) (2026)
- [VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip](https://mlsanity.com/paper/2508.10931/) (2025)
- [Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention](https://mlsanity.com/paper/2511.10268/) (2025)
- [Position: The Pitfalls of Over-Alignment: Overly Caution Health-Related Responses From LLMs are Unethical and Dangerous](https://mlsanity.com/paper/2509.08833/) (2025)
- [SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models](https://mlsanity.com/paper/2502.14908/) (2025)
- [ZS-VCOS: Zero-Shot Video Camouflaged Object Segmentation By Optical Flow and Open Vocabulary Object Detection](https://mlsanity.com/paper/2505.01431/) (2025)

## Abstract (arXiv)

Vision Language Models (VLMs) are well known for hallucinating non-existent objects in images. Objects with missing parts present a unique challenge for VLMs, stemming from both real-world knowledge bias and the scarcity of such images in training data. We present MissingBench-Verified, a benchmark designed to evaluate a specific and practically relevant scenario: when vision-language models fail to recognize that an essential component of an object has been removed. Across ten leading models, we observe consistent and significant failure rates that persist even when external tool evidence explicitly contradicts the model's visual perception. We further ask whether granting models access to image processing tools (e.g., cropping, contrast adjustment) enables autonomous inspection to resolve these failures. We find that existing mitigation strategies, including tool-assisted verification, autonomous visual reasoning, longer reasoning durations, and fine-tuning on an easier dataset, provide negligible improvement, indicating that this failure mode cannot be addressed through current prompting or post-hoc correction techniques. Our findings highlight a fundamental limitation of current VLM for inspection and monitoring tasks and underscore the need for architectural or training-level interventions that enable models to override internal expectations when confronted with contradictory evidence.