Metraipolis › archive › dc_fbaffea15c55

Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models — arXiv:2610.10508

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.10508
License (as archived): CC0-1.0
Archived: 2026-10-08T11:26:25.075Z
SHA-256 of the archived text: f5657379cc527fd47cb917d0931fe4072000cab571f4a243b4be167475d82c96
Stable URL of this page: https://metraipolis.com/documento/dc_fbaffea15c55

How to cite

Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models — arXiv:2610.10508 — arXiv (en), https://arxiv.org/abs/2610.10508 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fbaffea15c55 (Metraipolis archive dc_fbaffea15c55, sha256 f5657379cc527fd47cb917d0931fe4072000cab571f4a243b4be167475d82c96)

BibTeX

@misc{dcfbaffea15c55,
  title = {Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models — arXiv:2610.10508},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10508},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fbaffea15c55; sha256 f5657379cc527fd47cb917d0931fe4072000cab571f4a243b4be167475d82c96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10508. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as part of the retrieval prompt. Several new datasets and studies have examined this setting, showing that the current embedding models often struggle to follow such instructions reliably. In this paper, we study the mechanism of how instructions actually affect the representations of retrieval queries in asymmetric retrieval tasks. We show that models can fail to follow even simple task instructions when query-side distractors are included in the evaluation. We hypothesize that this behavior is driven by the training setup of current embedding models and their evaluation, and show that fine-tuning with added query-side distractors leads to substantial improvements, with minimal effect on other tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.10508 — 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 2026-10-08T10:24:06.356Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).