Metraipolis › archive › dc_dd5ae2a2d9b4

Mapping Similarity Spaces across Embedding Models with Synthetic Query Probing — arXiv:2608.05857

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05857
License (as archived)
CC0-1.0
Archived
2026-10-25T21:27:18.121Z
SHA-256 of the archived text
906758001045f11199fd76c6d162af464d6df81b135a16832f5ebc9d014cee8c
Stable URL of this page
https://metraipolis.com/documento/dc_dd5ae2a2d9b4

How to cite

Mapping Similarity Spaces across Embedding Models with Synthetic Query Probing — arXiv:2608.05857 — arXiv (en), https://arxiv.org/abs/2608.05857 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd5ae2a2d9b4 (Metraipolis archive dc_dd5ae2a2d9b4, sha256 906758001045f11199fd76c6d162af464d6df81b135a16832f5ebc9d014cee8c)
BibTeX
@misc{dcdd5ae2a2d9b4,
  title = {Mapping Similarity Spaces across Embedding Models with Synthetic Query Probing — arXiv:2608.05857},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05857},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd5ae2a2d9b4; sha256 906758001045f11199fd76c6d162af464d6df81b135a16832f5ebc9d014cee8c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05857. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-Augmented Generation systems rely on similarity scores to retrieve relevant content, yet scores are not directly comparable across embedding models due to differing geometric properties, complicating model migration and limiting threshold reuse. We study how similarity scores can be related by learning mappings between score distributions rather than embeddings. We introduce Synthetic Query Probing, generating queries from documents to create controlled query-chunk pairs, enabling large-scale, reference-free analysis of cross-model similarity behavior. We evaluate the approach on multiple embedding configurations and learn score conversion functions using linear, isotonic, and quantile mappings. Experiments on SciFact and a proprietary corpus show that while models largely agree on rankings, their absolute scores exhibit systematic distortions. Learned mappings partially align these spaces and improve threshold portability, with isotonic regression performing best. Our results highlight the need for cross-model calibration and position Synthetic Query Probing as a scalable framework for analyzing embedding comparability.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.05857 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-25T21:24:38.215Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).