# Arbitration Failure, Not Perceptual Blindness: How Vision-Language Models Resolve Visual-Linguistic Conflicts

arXiv: https://arxiv.org/abs/2604.09364 · HTML: https://mlsanity.com/paper/2604.09364/

## Key facts

- Cited by 11 papers 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 19 of its 27 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)
- Mechanistic interpretability / [Interpreting vision and multimodal models](https://mlsanity.com/mechinterp/interpreting-vision-and-multimodal-models/)

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Towards Interpreting Visual Information Processing in Vision-Language Models](https://mlsanity.com/paper/2410.07149/) (2024)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models](https://mlsanity.com/paper/2504.02821/) (2025)
- [Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP](https://mlsanity.com/paper/2308.14179/) (2023)
- [Multimodal Neurons in Pretrained Text-Only Transformers](https://mlsanity.com/paper/2308.01544/) (2023)
- [Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts](https://mlsanity.com/paper/2505.17127/) (2025)

## Built on by (most cited first, 11 of 11)

- [Vision-Default, Prior-Override: Causal Mechanisms of Perception-Knowledge Conflict in Vision-Language Models](https://mlsanity.com/paper/2606.28273/) (2026)
- [Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs](https://mlsanity.com/paper/2605.13737/) (2026)
- [Diagnosing Visual Ignorance in Vision-Language Models](https://mlsanity.com/paper/2606.06890/) (2026)
- [From Accuracy to Visual Dependence: Auditing and Filtering Modality Collapse in Traffic VideoQA](https://mlsanity.com/paper/2606.30220/) (2026)
- [Knowing Isn't Always Saying: When Do Spatial Encodings Reach Answers in Vision-Language Models?](https://mlsanity.com/paper/2608.22916/) (2026)
- [Which Source Wins? Task-Dependent Reliance in Vision-Language Models](https://mlsanity.com/paper/2608.17205/) (2026)
- [Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and Cognition](https://mlsanity.com/paper/2609.07474/) (2026)
- [When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models](https://mlsanity.com/paper/2609.35272/) (2026)
- [A Low Grounding Score Is Not an Ungrounded Judge: Identifying the Perceptibility Confound in Multimodal Oversight](https://mlsanity.com/paper/2610.00111/) (2026)
- [Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally](https://mlsanity.com/paper/2610.03445/) (2026)
- [Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers](https://mlsanity.com/paper/2610.19407/) (2026)

## Abstract (arXiv)

When a Vision-Language Model (VLM) sees a blue banana and answers "yellow", is the problem of perception or arbitration? We explore the question in ten VLMs with various sizes and reveal an Encoding-Grounding Dissociation: models that fail to report what they see (and thus provide a wrong answer) still encode the visual evidence as strongly as models that provide the correct answer. Using Multimodal Arbitration Crossover (MAC) analysis with layer-by-layer Logit Lens probing, we track the competition between visual and prior signals across every layer of each model. We show that visual attributes can be linearly decodable from early layers (AUC > 0.86). The accuracy remains nearly identical for both successful and failed samples. However, the gap in the final-layer logit - not the strength of encoding - better predicts grounding outcomes with a correlation of ρ= 0.847. After having studied when VLMs base their answers on image clues rather than prior knowledge, we want to understand the causal relationships. We establish causality through full-sequence activation patching. The standard last-token interventions in LLM interpretability do not affect VLMs. In contrast, replacing the full token sequence at layers identified by MAC alters 60 to 84% of outputs. Partial-token decomposition shows that image tokens carry almost all of the causal impact, while text tokens have none. Scaling addresses the remaining architectural differences to achieve perfect retention. Moving from diagnosis to intervention, we show that training-free activation steering - both linear and sparse autoencoder-guided - in early layers can improve visual grounding by up to +3.8% with degrading performance in some setups. Overall, these findings lead to a clear conclusion: VLMs already see well, but the challenge is acting on what they see. Targeted interventions can help to bridge this gap.