Uncovering Entity Identity Confusion in Multimodal Knowledge Editing

• URL: http://arxiv.org/abs/2605.06096v1
• Date: Thu, 07 May 2026 12:14:54 GMT
• Title: Uncovering Entity Identity Confusion in Multimodal Knowledge Editing
• Abstract summary: Multimodal knowledge editing aims to correct the internal knowledge of large vision-language models after deployment.<n>We identify a systemic failure mode in edited models, termed Entity Identity Confusion (EIC)
• Score: 58.07263295190384
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing [52.315369633116255]
  Large language models (LLMs) are increasingly used as knowledge bases, but keeping them up to date requires targeted knowledge editing (KE)<n>We take a mechanistic view of KE using neuron-level knowledge attribution (NLKA)<n>Across representative KE methods, we find a consistent pattern: mid-to-late attention predominantly promotes the new target, while attention and FFN modules cooperate to suppress the original fact.<n>Motivated by these findings, we propose MEGA, a MEchanism-Guided Activation steering method that performs attention-residual interventions in attribution-aligned regions.
  arXiv  Detail & Related papers  (2026-03-21T12:40:15Z)
• Consistency-Aware Editing for Entity-level Unlearning in Language Models [53.522931419965424]
  We introduce a novel consistency-aware editing (CAE) framework for entity-level unlearning.<n>CAE aggregates a diverse set of prompts related to a target entity, including its attributes, relations, and adversarial paraphrases.<n>It then jointly learns a low-rank update guided by a consistency regularizer that aligns the editing directions across prompts.
  arXiv  Detail & Related papers  (2025-12-19T15:18:07Z)
• Disentangling Knowledge Representations for Large Language Model Editing [38.244171146682206]
  We propose DiKE, a novel approach that Disentangles Knowledge representations for LLM Editing.<n>DiKE consists of two key components: a Knowledge Representation Disentanglement (KRD) module that decomposes the subject representation into target-knowledgerelated and -unrelated components, and a Knowledge Edit (DKE) module that updates only the target-related component while explicitly preserving the unrelated one.<n>To rigorously evaluate fine-grained irrelevant knowledge preservation, we construct FINE-KED, a new benchmark comprising fine-grained irrelevant knowledge at different levels of relational similarity to the edited knowledge.
  arXiv  Detail & Related papers  (2025-05-24T16:24:04Z)
• Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject [49.559994791305535]
  Current state-of-the-art editing methods struggle when tasked with editing multiple related knowledge pieces for the same subject.<n>We introduce the $textS2textRKE$(Same-Subject Related Knowledge Editing) benchmark.<n>Our experiments reveal that only mainstream locate-then-edit methods, such as ROME and MEMIT, exhibit "related knowledge perturbation"
  arXiv  Detail & Related papers  (2025-02-08T04:47:17Z)
• Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning [54.69189620971405]
  We provide a unified framework, termed Identifiable Exchangeable Mechanisms (IEM), for representation and structure learning.<n>IEM provides new insights that let us relax the necessary conditions for causal structure identification in exchangeable non-i.i.d. data.<n>We also demonstrate the existence of a duality condition in identifiable representation learning, leading to new identifiability results.
  arXiv  Detail & Related papers  (2024-06-20T13:30:25Z)
• EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries [69.72012539060731]
  We introduce a theoretical framework for efficient knowledge editing (KE) in large language models (LLMs) We propose a novel task of event-based knowledge editing that pairs facts with event descriptions. We empirically demonstrate the superiority of event-based editing over the existing setting on resolving uncertainty in edited models.
  arXiv  Detail & Related papers  (2024-02-17T16:34:50Z)
• SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering [17.20346072074533]
  Recent model editing is a promising technique for efficiently updating a small amount of knowledge of large language models.<n>We propose a detachable and expandable Subject Word Embedding Altering (SWEA) framework, which finds the editing embeddings through token-level matching.<n>We demonstrate the overall state-of-the-art (SOTA) performance of SWEA$oplus$OS on the CounterFact and zsRE datasets.
  arXiv  Detail & Related papers  (2024-01-31T13:08:45Z)
• Entities as Experts: Sparse Memory Access with Entity Supervision [31.90630901747025]
  We introduce a new model - Entities as Experts (EAE) - that can access distinct memories of the entities mentioned in a piece of text. We show that EAE's learned representations capture sufficient knowledge to answer TriviaQA questions.
  arXiv  Detail & Related papers  (2020-04-15T17:00:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.