# When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models

arXiv: https://arxiv.org/abs/2507.13868 · HTML: https://mlsanity.com/paper/2507.13868/

## 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 36 of its 58 references that are in the map.
- First posted on arXiv 18 Jul 2025.

## 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, 30 of 36)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (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)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Retrieval Head Mechanistically Explains Long-Context Factuality](https://mlsanity.com/paper/2404.15574/) (2024)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges](https://mlsanity.com/paper/2311.03287/) (2023)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [Time Waits for No One! Analysis and Challenges of Temporal Misalignment](https://mlsanity.com/paper/2111.07408/) (2021)
- [Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2402.18154/) (2024)
- [Overthinking the Truth: Understanding how Language Models Process False Demonstrations](https://mlsanity.com/paper/2307.09476/) (2023)
- [Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images](https://mlsanity.com/paper/2303.07274/) (2023)
- [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)
- [Characterizing Mechanisms for Factual Recall in Language Models](https://mlsanity.com/paper/2310.15910/) (2023)
- [Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection](https://mlsanity.com/paper/2412.13817/) (2024)
- [PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset](https://mlsanity.com/paper/2403.11116/) (2024)
- [Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals](https://mlsanity.com/paper/2402.11655/) (2024)
- [COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs](https://mlsanity.com/paper/2309.14356/) (2023)
- [Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs](https://mlsanity.com/paper/2410.08145/) (2024)

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

- [Head Pursuit: Probing Attention Specialization in Multimodal Transformers](https://mlsanity.com/paper/2510.21518/) (2025)
- [Conflict Adaptation in Vision-Language Models](https://mlsanity.com/paper/2510.24804/) (2025)
- [CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models](https://mlsanity.com/paper/2605.17826/) (2026)
- [Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning](https://mlsanity.com/paper/2608.06938/) (2026)
- [Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models](https://mlsanity.com/paper/2605.22902/) (2026)
- [Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources](https://mlsanity.com/paper/2607.03365/) (2026)
- [Prior Directions: Why GUI Grounding Gets Locked in the Past](https://mlsanity.com/paper/2607.26913/) (2026)
- [GeoArbiter: Verifiability-Guided Grounding for Remote-Sensing Multimodal LLMs](https://mlsanity.com/paper/2608.00877/) (2026)
- [Which Source Wins? Task-Dependent Reliance in Vision-Language Models](https://mlsanity.com/paper/2608.17205/) (2026)
- [MoGround: Measuring and Mitigating Modality Distraction in Vision-Language Models](https://mlsanity.com/paper/2609.33431/) (2026)
- [When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models](https://mlsanity.com/paper/2609.35272/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) increasingly combine visual and textual information to perform complex tasks. However, conflicts between their internal knowledge and external visual input can lead to hallucinations and unreliable predictions. In this work, we investigate the mechanisms that VLMs use to resolve cross-modal conflicts by introducing WHOOPS-AHA!, a dataset of multimodal counterfactual queries that deliberately contradict internal commonsense knowledge. Through logit inspection, we identify a small set of attention heads that mediate this conflict. By intervening in these heads, we can steer the model towards its internal parametric knowledge or the visual information. Our results show that attention patterns on these heads effectively locate image regions that influence visual overrides, providing a more precise attribution compared to gradient-based methods.