Tinted Frames: Question Framing Blinds Vision-Language Models

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.

Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens. However, we observe that highest attention regions are not always consistent with the intended semantic token. This probably stems from decoding drift, where language priors from previously generated answer tokens accumulate and mismatch with visual attention. Besides the priors from previous answer tokens, we find that structural tokens, e.g., modality boundary markers, may encompass the entire context and generate high attention to areas unrelated to the target. To avoid these distortions and provide consistency evaluation for large VLMs, we adopt prompt-side semantics and propose Prompt-Vision Token Activation Map (PV-TAM). PV-TAM further incorporates a filter to remove systematic bias induced by modality boundary markers. Unlike traditional methods that evaluate overlap solely through masks while ignoring activation intensity, our metrics leverage the peak distribution of attention to measure the alignment between prompts and visual regions. In experiments, PV-TAM consistently improves both attention-based and IoU-style localization metrics over answer-side baselines on various datasets.

We introduce Self-Saliency, a method for training Vision-Language Models (VLMs) to increase the alignment between their visual attention and the image regions mentioned in their reasoning. Self-Saliency uses a grounding model to localize the objects mentioned in each reasoning step and treats the resulting areas as supervision for the model's visual attention. Previous work on steering visual attention determines target image regions based solely on the image and question. In contrast, we show that conditioning the target regions on the model's generated reasoning improves downstream performance. For proper evaluation, we build a unified, broad suite of 25 visual reasoning benchmarks, where we reproduce the results of previous methods. We find that Self-Saliency significantly outperforms both prior attention-steering methods and baselines that ground image-level text, achieving both a better average rank and a better mean score. Post-training analysis shows that the model primarily adapts its reasoning text to existing attention patterns, producing shorter steps that refer to larger regions. Nevertheless, when controlling for generated text, attention to grounded regions increases significantly across the relevant layer. Finally, we identify a consistent geometric bias in VLM visual attention toward the image border. However, our ablations show that Self-Saliency's gains cannot be explained by simply aligning attention with the center of the image, highlighting the importance of aligning visual attention with the regions mentioned in the model's reasoning.