Editing Across Languages: A Survey of Multilingual Knowledge Editing

• URL: http://arxiv.org/abs/2505.14393v1
• Date: Tue, 20 May 2025 14:13:04 GMT
• Title: Editing Across Languages: A Survey of Multilingual Knowledge Editing
• Authors: Nadir Durrani, Basel Mousi, Fahim Dalvi,
• Abstract summary: This survey systematizes recent research on Multilingual Knowledge Editing (MKE)<n>MKE is a growing subdomain of model editing focused on ensuring factual edits generalize reliably across languages.<n>We present a comprehensive taxonomy of MKE methods, covering parameter-based, memory-based, fine-tuning, and hypernetwork approaches.
• Score: 16.700978644147572
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models [16.546605509744015]
  We introduce UniEdit, a unified benchmark for large language models (LLMs) editing grounded in open-domain knowledge.<n>First, we construct editing samples by selecting entities from 25 common domains across five major categories.<n>To address the issues of generality and locality in editing, we design an Neighborhood Multi-hop Chain Sampling (NMCS) algorithm.
  arXiv  Detail & Related papers  (2025-05-18T10:19:01Z)
• Cross-Lingual Multi-Hop Knowledge Editing [53.028586843468915]
  We propose the Cross-Lingual Multi-Hop Knowledge Editing paradigm, for measuring and analyzing the performance of various SoTA knowledge editing techniques in a cross-lingual setup.<n>Specifically, we create a parallel cross-lingual benchmark, CROLIN-MQUAKE for measuring the knowledge editing capabilities.<n>Following this, we propose a significantly improved system for cross-lingual multi-hop knowledge editing, CLEVER-CKE.
  arXiv  Detail & Related papers  (2024-07-14T17:18:16Z)
• Multilingual Knowledge Editing with Language-Agnostic Factual Neurons [98.73585104789217]
  Same factual knowledge in different languages generally activates a shared set of neurons, which we call language-agnostic factual neurons (LAFNs)<n>These neurons represent the same factual knowledge shared across languages and imply the semantic connections among multilingual knowledge.<n>We propose a new MKE method by Locating and Updating Language-Agnostic Factual Neurons (LU-LAFNs) to edit multilingual knowledge simultaneously.
  arXiv  Detail & Related papers  (2024-06-24T08:06:56Z)
• MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation [18.087144677674786]
  We focus on multilingual knowledge editing (MKE), which requires propagating updates across multiple languages. We introduce the Multilingual Knowledge Editing Benchmark (MKEB), a novel dataset comprising 12 languages. We also propose a method that enhances knowledge Editing with neuron-Masked Low-Rank Adaptation (MEMLA)
  arXiv  Detail & Related papers  (2024-06-17T14:03:50Z)
• A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers [51.8203871494146]
  The rapid development of Large Language Models (LLMs) demonstrates remarkable multilingual capabilities in natural language processing.<n>Despite the breakthroughs of LLMs, the investigation into the multilingual scenario remains insufficient.<n>This survey aims to help the research community address multilingual problems and provide a comprehensive understanding of the core concepts, key techniques, and latest developments in multilingual natural language processing based on LLMs.
  arXiv  Detail & Related papers  (2024-05-17T17:47:39Z)
• MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models [65.10456412127405]
  MLaKE is a benchmark for the adaptability of knowledge editing methods across five languages.<n>MLaKE aggregates fact chains from Wikipedia across languages and generates questions in both free-form and multiple-choice.<n>We evaluate the multilingual knowledge editing generalization capabilities of existing methods on MLaKE.
  arXiv  Detail & Related papers  (2024-04-07T15:23:28Z)
• Retrieval-augmented Multilingual Knowledge Editing [81.6690436581947]
  Knowledge represented in Large Language Models (LLMs) is quite often incorrect and can also become obsolete over time. Knowledge editing (KE) has developed as an effective and economical alternative to inject new knowledge. We propose Retrieval-augmented Multilingual Knowledge Editor (ReMaKE) to update new knowledge in LLMs.
  arXiv  Detail & Related papers  (2023-12-20T14:08:58Z)
• Cross-Lingual Knowledge Editing in Large Language Models [73.12622532088564]
  Knowledge editing has been shown to adapt large language models to new knowledge without retraining from scratch. It is still unknown the effect of source language editing on a different target language. We first collect a large-scale cross-lingual synthetic dataset by translating ZsRE from English to Chinese.
  arXiv  Detail & Related papers  (2023-09-16T11:07:52Z)

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.