{
  "id": 5959,
  "url": "https://arxiv.org/abs/2604.11096v1",
  "title": "Efficient Training for Cross-lingual Speech Language Models",
  "summary": "Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data and the difficulty in expanding to more languages. In this paper, we introduce Cross-lingual Speech Language Model (CSLM), an efficient training method for cross-lingual speech LLMs based on discrete speech tokens. We propose a novel alignment strategy that ach",
  "authors": "Yan Zhou, Qingkai Fang, Yun Hong, Yang Feng",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-13T07:12:40.000Z",
  "fetched_at": "2026-07-14T16:32:06.471Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5959",
  "original_url": "https://arxiv.org/abs/2604.11096v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}