Editing Across Languages: A Survey of Multilingual Knowledge Editing

TL;DR

This survey reviews recent advances in Multilingual Knowledge Editing, focusing on methods, benchmarks, and challenges in ensuring factual edits in language models generalize across multiple languages.

Contribution

It provides a comprehensive taxonomy of MKE methods, summarizes key findings, and identifies open challenges, guiding future research in multilingual model editing.

Findings

Parameter-based and memory-based methods vary in effectiveness

Transfer patterns depend on language similarity and model architecture

Significant challenges remain in cross-lingual propagation and scalability

Abstract

While Knowledge Editing has been extensively studied in monolingual settings, it remains underexplored in multilingual contexts. This survey systematizes recent research on Multilingual Knowledge Editing (MKE), a growing subdomain of model editing focused on ensuring factual edits generalize reliably across languages. We present a comprehensive taxonomy of MKE methods, covering parameter-based, memory-based, fine-tuning, and hypernetwork approaches. We survey available benchmarks,summarize key findings on method effectiveness and transfer patterns, identify challenges in cross-lingual propagation, and highlight open problems related to language anisotropy, evaluation coverage, and edit scalability. Our analysis consolidates a rapidly evolving area and lays the groundwork for future progress in editable language-aware LLMs.