Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharing

• URL: http://arxiv.org/abs/2510.07736v1
• Date: Thu, 09 Oct 2025 03:19:21 GMT
• Title: Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharing
• Authors: Cunli Mao, Xiaofei Gao, Ran Song, Shizhu He, Shengxiang Gao, Kang Liu, Zhengtao Yu,
• Abstract summary: We propose a novel MKGC framework that leverages multilingual shared knowledge to significantly enhance performance.<n>Our framework achieves improvements of 5.47%, 3.27%, and 1.01% in the Hits@1, Hits@3, and Hits@10 metrics, respectively.
• Score: 37.388717962554715
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models (LLMs) based Multilingual Knowledge Graph Completion (MKGC) aim to predict missing facts by leveraging LLMs' multilingual understanding capabilities, improving the completeness of multilingual knowledge graphs (KGs). However, existing MKGC research underutilizes the multilingual capabilities of LLMs and ignores the shareability of cross-lingual knowledge. In this paper, we propose a novel MKGC framework that leverages multilingual shared knowledge to significantly enhance performance through two components: Knowledge-level Grouped Mixture of Experts (KL-GMoE) and Iterative Entity Reranking (IER). KL-GMoE efficiently models shared knowledge, while IER significantly enhances its utilization. To evaluate our framework, we constructed a mKG dataset containing 5 languages and conducted comprehensive comparative experiments with existing state-of-the-art (SOTA) MKGC method. The experimental results demonstrate that our framework achieves improvements of 5.47%, 3.27%, and 1.01% in the Hits@1, Hits@3, and Hits@10 metrics, respectively, compared with SOTA MKGC method. Further experimental analysis revealed the properties of knowledge sharing in settings of unseen and unbalanced languages. We have released the dataset and code for our work on https://github.com/gaoxiaofei07/KL-GMoE.

Related papers

• Measuring the Effect of Disfluency in Multilingual Knowledge Probing Benchmarks [27.561894897347376]
  We compare knowledge retrieval scores between the initial (templated) MLAMA dataset and its sentence-level translations made by Google Translate and ChatGPT.<n>We observe a significant increase in knowledge retrieval scores, and provide a qualitative analysis for possible reasons behind it.<n>We also make an additional analysis of 5 more languages from different families and see similar patterns.
  arXiv  Detail & Related papers  (2025-10-16T20:16:56Z)
• Retrieval-Augmented Machine Translation with Unstructured Knowledge [63.97706326080482]
  Retrieval-augmented generation (RAG) introduces additional information to enhance large language models (LLMs)<n>In machine translation (MT), previous work typically retrieves in-context examples from paired MT corpora, or domain-specific knowledge from knowledge graphs.<n>In this paper, we study retrieval-augmented MT using unstructured documents.
  arXiv  Detail & Related papers  (2024-12-05T17:00:32Z)
• 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)
• Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters [3.7273829129985305]
  This paper explores integration of graph knowledge from linguistic into multilingual Large Models (LLMs)<n>We employ language-specific adapters to improve performance for low-resource languages (LRLs) in sentiment analysis (SA) and named entity recognition (NER)<n>We assess how structured graph knowledge affects the performance of multilingual LLMs for LRLs in SA and NER.
  arXiv  Detail & Related papers  (2024-07-01T15:56:24Z)
• Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints [34.66309564398462]
  This paper introduces global and local knowledge constraints for mKGC. Experimental results on public datasets demonstrate that our method outperforms the previous SOTA on Hits@1 and Hits@10.
  arXiv  Detail & Related papers  (2024-06-26T05:46:35Z)
• BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning [43.059873703788206]
  This paper introduces BMIKE-53, a benchmark for cross-lingual in-context knowledge editing (IKE) across 53 languages.<n>Cross-lingual KE requires knowledge edited in one language to generalize across others while preserving unrelated knowledge.<n>Our findings reveal that model scale and demonstration alignment critically govern cross-lingual IKE efficacy.
  arXiv  Detail & Related papers  (2024-06-25T17:48:56Z)
• Adapters for Enhanced Modeling of Multilingual Knowledge and Text [54.02078328453149]
  Language models have been extended to multilingual language models (MLLMs) Knowledge graphs contain facts in an explicit triple format, which require careful curation and are only available in a few high-resource languages. We propose to enhance MLLMs with knowledge from multilingual knowledge graphs (MLKGs) so as to tackle language and knowledge graph tasks across many languages.
  arXiv  Detail & Related papers  (2022-10-24T21:33:42Z)
• Prix-LM: Pretraining for Multilingual Knowledge Base Construction [59.02868906044296]
  We propose a unified framework, Prix-LM, for multilingual knowledge construction and completion. We leverage two types of knowledge, monolingual triples and cross-lingual links, extracted from existing multilingual KBs. Experiments on standard entity-related tasks, such as link prediction in multiple languages, cross-lingual entity linking and bilingual lexicon induction, demonstrate its effectiveness.
  arXiv  Detail & Related papers  (2021-10-16T02:08:46Z)
• Explicit Alignment Objectives for Multilingual Bidirectional Encoders [111.65322283420805]
  We present a new method for learning multilingual encoders, AMBER (Aligned Multilingual Bi-directional EncodeR) AMBER is trained on additional parallel data using two explicit alignment objectives that align the multilingual representations at different granularities. Experimental results show that AMBER obtains gains of up to 1.1 average F1 score on sequence tagging and up to 27.3 average accuracy on retrieval over the XLMR-large model.
  arXiv  Detail & Related papers  (2020-10-15T18:34:13Z)

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.