{
  "id": 3436,
  "url": "https://arxiv.org/abs/2605.31171v1",
  "title": "MIMO: Multilingual Information Retrieval via Monolingual Objectives",
  "summary": "Multilingual Information Retrieval (MLIR) reflects real-world search environments in which queries and relevant documents may appear in different languages within a mixed-language corpus. However, existing embedding models are primarily optimized for Multi-Monolingual retrieval and their performance often degrades in MLIR settings. Moreover, directly applying conventional contrastive learning to MLIR can exacerbate language clustering and expose a trade-off between cross-lingual alignment and em",
  "authors": "Youngjoon Jang, Seongtae Hong, Heuiseok Lim",
  "category": "research",
  "topics": "safety-alignment,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-29T11:34:15.000Z",
  "fetched_at": "2026-07-14T16:30:14.371Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3436",
  "original_url": "https://arxiv.org/abs/2605.31171v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}