{
  "annotation_id": "1afb9c81-5fe8-4fde-97b9-e5c7aaac8b7c",
  "date_created": "2026-02-17T05:53:24.166000Z",
  "date_modified": "2026-02-17T05:53:24.166000Z",
  "file_hash": "39a116ffc8a97912d7d70167d0e0e1c75484bcc790422e6f0f2265393e62c5dc",
  "private": false,
  "record": {
    "abstract": "With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB) may mask fundamental alignment shortcomings. We introduce Semantic Affinity (SA), a bounded (between 0 and 1) metric measuring inter-lingual to intra-lingual spread ratio using cosine distance, combined with PHATE visualization in our Semanscope framework. Benchmarking 13 models across 4 datasets (52 experiments) reveals a three-tier structure: (1) Top BERT models (LaBSE SA = 0.70, USE SA = 0.68, S-BERT SA = 0.68) achieve strong alignment via translation-pair supervision; (2) LLM embeddings plateau at SA between 0.55 and 0.61 regardless of 0.6 B to 8 B scale; (3) MLM-only BERT models (mBERT, XLM-R, SA \u003c 0.50) fail despite more than 100 language training. Training objective, not architecture or scale, determines alignment. Oracle Bone primitives (1200 BCE) expose semantic drift-models learn corpus patterns rather than cognitive primitives. This work provides semantic benchmarking to help practitioners select quality multilingual embeddings from hundreds of available models, showing cross-lingual alignment requires explicit translation supervision, not merely model scale or multilingual data.",
    "arxiv_id": "2601.09732",
    "authors": [
      "Wen G. Gong"
    ],
    "categories": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Benchmarking Cross-Lingual Semantic Alignment in Multilingual Embeddings",
    "url": "https://arxiv.org/abs/2601.09732",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "ba1c3662-a11b-4ef3-94fa-026099c61a28",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}