# Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation

arXiv: https://arxiv.org/abs/2511.05923 · HTML: https://mlsanity.com/paper/2511.05923/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 8 Nov 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)
- Mechanistic interpretability / [Interpreting vision and multimodal models](https://mlsanity.com/mechinterp/interpreting-vision-and-multimodal-models/)

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (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)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation](https://mlsanity.com/paper/2311.17911/) (2023)
- [Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP](https://mlsanity.com/paper/2308.14179/) (2023)
- [Reducing Hallucinations in Vision-Language Models via Latent Space Steering](https://mlsanity.com/paper/2410.15778/) (2024)
- [M2IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering](https://mlsanity.com/paper/2504.04633/) (2025)
- [Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization](https://mlsanity.com/paper/2405.15356/) (2024)
- [TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration](https://mlsanity.com/paper/2505.17098/) (2025)
- [CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning](https://mlsanity.com/paper/2508.07871/) (2025)
- [CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention](https://mlsanity.com/paper/2506.11073/) (2025)

## Built on by (most cited first, 23 of 23)

- [Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering](https://mlsanity.com/paper/2511.23231/) (2025)
- [Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models](https://mlsanity.com/paper/2604.01840/) (2026)
- [Dual-Pathway Circuits of Object Hallucination in Vision-Language Models](https://mlsanity.com/paper/2605.13156/) (2026)
- [MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents](https://mlsanity.com/paper/2512.00756/) (2025)
- [Causal Tracing of Audio-Text Fusion in Large Audio Language Models](https://mlsanity.com/paper/2603.13768/) (2026)
- [Probing Cross-modal Information Hubs in Audio-Visual LLMs](https://mlsanity.com/paper/2605.10815/) (2026)
- [Pathways of Visual Information Flow in Vision-Language Models](https://mlsanity.com/paper/2607.03358/) (2026)
- [Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads](https://mlsanity.com/paper/2606.05843/) (2026)
- [SlowBA: An efficiency backdoor attack towards VLM-based GUI agents](https://mlsanity.com/paper/2603.08316/) (2026)
- [Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision](https://mlsanity.com/paper/2511.07062/) (2025)
- [Responses Fall Short of Understanding: Revealing the Gap between Internal Representations and Responses in Visual Document Understanding](https://mlsanity.com/paper/2604.04411/) (2026)
- [Mechanisms of Object Localization in Vision-Language Models](https://mlsanity.com/paper/2605.19792/) (2026)
- [When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities](https://mlsanity.com/paper/2607.08605/) (2026)
- [Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information](https://mlsanity.com/paper/2608.27417/) (2026)
- [Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2608.30649/) (2026)
- [Mechanistically Interpreting Compression in Vision-Language Models](https://mlsanity.com/paper/2603.25035/) (2026)
- [Sparse Visual Thought Circuits in Vision-Language Models](https://mlsanity.com/paper/2603.25075/) (2026)
- [CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering](https://mlsanity.com/paper/2605.04641/) (2026)
- [Don't Look at the Numbers: Visual Anchoring Bias and Layer-wise Representation in VLMs](https://mlsanity.com/paper/2605.11218/) (2026)
- [Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow](https://mlsanity.com/paper/2605.21980/) (2026)
- [Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models](https://mlsanity.com/paper/2605.29826/) (2026)
- [How Do VLMs Fail? Vision-Operation Misalignment in Compositional VQA](https://mlsanity.com/paper/2607.16094/) (2026)
- [When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models](https://mlsanity.com/paper/2608.18628/) (2026)

## Abstract (arXiv)

Despite the remarkable advancements of Large Vision-Language Models (LVLMs), the mechanistic interpretability remains underexplored. Existing analyses are insufficiently comprehensive and lack examination covering visual and textual tokens, model components, and the full range of layers. This limitation restricts actionable insights to improve the faithfulness of model output and the development of downstream tasks, such as hallucination mitigation. To address this limitation, we introduce Fine-grained Cross-modal Causal Tracing (FCCT) framework, which systematically quantifies the causal effects on visual object perception. FCCT conducts fine-grained analysis covering the full range of visual and textual tokens, three core model components including multi-head self-attention (MHSA), feed-forward networks (FFNs), and hidden states, across all decoder layers. Our analysis is the first to demonstrate that MHSAs of the last token in middle layers play a critical role in aggregating cross-modal information, while FFNs exhibit a three-stage hierarchical progression for the storage and transfer of visual object representations. Building on these insights, we propose Intermediate Representation Injection (IRI), a training-free inference-time technique that reinforces visual object information flow by precisely intervening on cross-modal representations at specific components and layers, thereby enhancing perception and mitigating hallucination. Consistent improvements across five widely used benchmarks and LVLMs demonstrate IRI achieves state-of-the-art performance, while preserving inference speed and other foundational performance.