# Uncovering Entity Identity Confusion in Multimodal Knowledge Editing

arXiv: https://arxiv.org/abs/2605.06096 · HTML: https://mlsanity.com/paper/2605.06096/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 29 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)

## Builds on (most cited first, 26 of 26)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [MMKG: Multi-Modal Knowledge Graphs](https://mlsanity.com/paper/1903.05485/) (2019)
- [EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models](https://mlsanity.com/paper/2308.07269/) (2023)
- [Can We Edit Multimodal Large Language Models?](https://mlsanity.com/paper/2310.08475/) (2023)
- [Knowledge Graph Enhanced Large Language Model Editing](https://mlsanity.com/paper/2402.13593/) (2024)
- [Uncovering Overfitting in Large Language Model Editing](https://mlsanity.com/paper/2410.07819/) (2024)
- [VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark](https://mlsanity.com/paper/2403.07350/) (2024)
- [MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing](https://mlsanity.com/paper/2402.14835/) (2024)
- [MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency](https://mlsanity.com/paper/2406.13219/) (2024)
- [Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration](https://mlsanity.com/paper/2409.19872/) (2024)
- [Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models](https://mlsanity.com/paper/2411.12790/) (2024)
- [Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval](https://mlsanity.com/paper/2512.03276/) (2025)
- [Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse](https://mlsanity.com/paper/2601.11042/) (2026)
- [Uncovering Context Reliance in Unstructured Knowledge Editing](https://mlsanity.com/paper/2602.19043/) (2026)

## Built on by (most cited first, 1 of 1)

- [Generalizable Model Editing Could Be More Than Direct Generalization](https://mlsanity.com/paper/2610.15707/) (2026)

## Abstract (arXiv)

Multimodal knowledge editing (MKE) aims to correct the internal knowledge of large vision-language models after deployment, yet the behavioral patterns of post-edit models remain underexplored. In this paper, we identify a systemic failure mode in edited models, termed Entity Identity Confusion (EIC): edited models exhibit an absurd behavior where text-only queries about the original entity's identity unexpectedly return information about the new entity. To rigorously investigate EIC, we construct EC-Bench, a diagnostic benchmark that directly probes how image-entity bindings shift before and after editing. Our analysis reveals that EIC stems from existing methods failing to distinguish between Image-Entity (I-E) binding and Entity-Entity (E-E) relational knowledge in the model, causing models to overfit E-E associations as a shortcut: the image is still perceived as the original entity, with the new entity's name serving only as a spurious identity label. We further explore potential mitigation strategies, showing that constraining edits to the model's I-E processing stage encourages edits to act more faithfully on I-E binding, thereby substantially reducing EIC. Based on these findings, we discuss principled desiderata for faithful MKE and provide methodological guidance for future research.