# Cross-lingual Editing in Multilingual Language Models

arXiv: https://arxiv.org/abs/2401.10521 · HTML: https://mlsanity.com/paper/2401.10521/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jan 2024.

## Built on by (most cited first, 18 of 18)

- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs](https://mlsanity.com/paper/2408.10646/) (2024)
- [Multilingual Knowledge Editing with Language-Agnostic Factual Neurons](https://mlsanity.com/paper/2406.16416/) (2024)
- [A First Look at GPT Apps: Landscape and Vulnerability](https://mlsanity.com/paper/2402.15105/) (2024)
- [BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning](https://mlsanity.com/paper/2406.17764/) (2024)
- [Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models](https://mlsanity.com/paper/2406.16135/) (2024)
- [MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation](https://mlsanity.com/paper/2406.11566/) (2024)
- [Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?](https://mlsanity.com/paper/2507.12838/) (2025)
- [Decoding the Diversity: A Review of the Indic AI Research Landscape](https://mlsanity.com/paper/2406.09559/) (2024)
- [Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance](https://mlsanity.com/paper/2406.11139/) (2024)
- [Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence](https://mlsanity.com/paper/2411.07533/) (2024)
- [Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification](https://mlsanity.com/paper/2505.16722/) (2025)
- [Measuring the Effect of Disfluency in Multilingual Knowledge Probing Benchmarks](https://mlsanity.com/paper/2510.15115/) (2025)
- [Editing Across Languages: A Survey of Multilingual Knowledge Editing](https://mlsanity.com/paper/2505.14393/) (2025)
- [An Exploration of Knowledge Editing for Arabic](https://mlsanity.com/paper/2507.09629/) (2025)
- [CLM-Bench: Benchmarking and Analyzing Cross-lingual Misalignment of LLMs in Knowledge Editing](https://mlsanity.com/paper/2601.17397/) (2026)
- [Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs](https://mlsanity.com/paper/2606.22627/) (2026)
- [Why Pretraining Fails to Share Cross-Lingual Knowledge](https://mlsanity.com/paper/2609.19291/) (2026)

## Abstract (arXiv)

The training of large language models (LLMs) necessitates substantial data and computational resources, and updating outdated LLMs entails significant efforts and resources. While numerous model editing techniques (METs) have emerged to efficiently update model outputs without retraining, their effectiveness in multilingual LLMs, where knowledge is stored in diverse languages, remains an underexplored research area. This research paper introduces the cross-lingual model editing (XME) paradigm, wherein a fact is edited in one language, and the subsequent update propagation is observed across other languages. To investigate the XME paradigm, we conducted experiments using BLOOM, mBERT, and XLM-RoBERTa using the two writing scripts: textitLatin (English, French, and Spanish) and textitIndic (Hindi, Gujarati, and Bengali). The results reveal notable performance limitations of state-of-the-art METs under the XME setting, mainly when the languages involved belong to two distinct script families. These findings highlight the need for further research and development of XME techniques to address these challenges. For more comprehensive information, the dataset used in this research and the associated code are publicly available at the following URLurlhttps://github.com/lingo-iitgn/XME.