Metraipolis › archive › dc_12eae8423697

Retrieval Sensitivity to Identity Signals in Queries — arXiv:2609.36534

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.36534
License (as archived): CC0-1.0
Archived: 2026-10-07T16:56:34.196Z
SHA-256 of the archived text: 77fff08fbd5f8b7f58bcac7064f77d65c37767b7c357eef79a356c6285528ab7
Stable URL of this page: https://metraipolis.com/documento/dc_12eae8423697

How to cite

Retrieval Sensitivity to Identity Signals in Queries — arXiv:2609.36534 — arXiv (en), https://arxiv.org/abs/2609.36534 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_12eae8423697 (Metraipolis archive dc_12eae8423697, sha256 77fff08fbd5f8b7f58bcac7064f77d65c37767b7c357eef79a356c6285528ab7)

BibTeX

@misc{dc12eae8423697,
  title = {Retrieval Sensitivity to Identity Signals in Queries — arXiv:2609.36534},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36534},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_12eae8423697; sha256 77fff08fbd5f8b7f58bcac7064f77d65c37767b7c357eef79a356c6285528ab7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36534. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Dense retrievers decide which documents reach users and the language models that use them, yet they are typically evaluated with neutral queries. We ask whether the identity signals that real users express in their queries---political ideology and dialect---bias what a retriever returns. We design evaluations in two domains, political news and consumer-health questions, each pairing a controlled synthetic set that varies only the identity signal with naturalistic queries. Across five dense retrievers and a sparse baseline, every retriever (i) retrieves articles that align with the query's own political lean and (ii) performs worse for questions written in African American Language (AAL) than in White Mainstream English (WME). Two analyses tie these gaps to queries' identity signals beyond surface vocabulary: partialling out an aggregate lexical-asymmetry score leaves the synthetic gaps largely intact, and linear probes recover lean and dialect from the retrievers' query embeddings beyond token-level features. Left unaddressed, such retrieval biases risk contributing to polarization and reinforcing the health disparities already faced by AAL speakers. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Computers and Society (cs.CY); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.36534 — 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 2026-10-07T16:27:03.214Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).