{
  "id": 16554901,
  "title": "Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model",
  "url": "https://urgent.news/2026/10/23/yalda-embedding-open-development-of-a-competitive-persian-retrieval",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-23T17:30:40.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.32933v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by the limited availability of language-specific training resources and compact embedding models. We present Yalda Embedding, a 595.8-million-parameter Persian retrieval model adapted from Qwen3-Embedding-0.6B using more than one million query-document pairs. On eight Persian retrieval…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}