Metraipolis › archive › dc_672da5ec7888

When Can We Work in Embedding Space? What Text Embeddings Preserve — arXiv:2608.31059

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.31059
License (as archived)
CC0-1.0
Archived
2026-10-17T08:10:12.026Z
SHA-256 of the archived text
75d76dae61a5130adc6aaceab51e244ed5780a706ee109be33631e3b33a70f41
Stable URL of this page
https://metraipolis.com/documento/dc_672da5ec7888

How to cite

When Can We Work in Embedding Space? What Text Embeddings Preserve — arXiv:2608.31059 — arXiv (en), https://arxiv.org/abs/2608.31059 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_672da5ec7888 (Metraipolis archive dc_672da5ec7888, sha256 75d76dae61a5130adc6aaceab51e244ed5780a706ee109be33631e3b33a70f41)
BibTeX
@misc{dc672da5ec7888,
  title = {When Can We Work in Embedding Space? What Text Embeddings Preserve — arXiv:2608.31059},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.31059},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_672da5ec7888; sha256 75d76dae61a5130adc6aaceab51e244ed5780a706ee109be33631e3b33a70f41},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.31059. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When do text embeddings work as inputs to empirical analysis? Their use rests on an assumption: that we can trade text for its low-dimensional embedding, and lose little in doing so. I make that assumption precise under a generative model in which documents are mixtures of latent topics. I study two uses---clustering units in embedding space and controlling for high-dimensional text. A cluster of embeddings is a set of documents with similar topic mixtures; controlling for the embedding is equivalent to controlling for the topic mixture, so validity reduces to whether that mixture captures the confounding. In an application to 363 U.S. metropolitan areas, embedding-based clusters of LLM-generated economic descriptions recover interpretable economic archetypes and separate local employment dynamics more sharply than clustering on model residuals, or on a curated set of industry and demographic covariates.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Econometrics (econ.EM) ; Computation and Language (cs.CL); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.31059 — 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 2026-10-17T07:47:52.942Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).