{
  "id": 6003,
  "url": "https://arxiv.org/abs/2604.10590v1",
  "title": "Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance",
  "summary": "Multilingual Large Language Models (LLMs) struggle with cross-lingual tasks due to data imbalances between high-resource and low-resource languages, as well as monolingual bias in pre-training. Existing methods, such as bilingual fine-tuning and contrastive alignment, can improve cross-lingual performance, but they often require extensive parallel data or suffer from instability. To address these challenges, we introduce a Cross-Lingual Mapping Task during the pre-training phase, which enhances ",
  "authors": "Weihua Zheng, Chang Liu, Zhengyuan Liu, Xin Huang, Kui Wu, Muhammad Huzaifah Md Shahrin et al.",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-12T11:43:25.000Z",
  "fetched_at": "2026-07-14T16:32:11.182Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6003",
  "original_url": "https://arxiv.org/abs/2604.10590v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}