Editing Across Languages: A Survey of Multilingual Knowledge Editing
It tackles the problem of making language model edits work consistently across multiple languages for researchers and practitioners, but it is incremental as a survey that organizes existing work rather than introducing new methods.
This survey addresses the underexplored problem of Multilingual Knowledge Editing (MKE) by systematizing research to ensure factual edits generalize reliably across languages, consolidating methods, benchmarks, and challenges in the field.
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.