Metraipolis › archive › dc_02e2d5ee3664

Retrieval-Based In-Context Learning: A Domain Adaptation Framework — arXiv:2610.05717

Source
arXiv
Original
https://arxiv.org/abs/2610.05717
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:21.297Z
SHA-256 of the archived text
02bf1059ff8f1c1e5ed5db69b9cd74e778ffa8575af816df23cd778d2babfe4f
Stable URL of this page
https://metraipolis.com/documento/dc_02e2d5ee3664

How to cite

Retrieval-Based In-Context Learning: A Domain Adaptation Framework — arXiv:2610.05717 — arXiv, https://arxiv.org/abs/2610.05717 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02e2d5ee3664 (Metraipolis archive dc_02e2d5ee3664, sha256 02bf1059ff8f1c1e5ed5db69b9cd74e778ffa8575af816df23cd778d2babfe4f)
BibTeX
@misc{dc02e2d5ee3664,
  title = {Retrieval-Based In-Context Learning: A Domain Adaptation Framework — arXiv:2610.05717},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05717},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02e2d5ee3664; sha256 02bf1059ff8f1c1e5ed5db69b9cd74e778ffa8575af816df23cd778d2babfe4f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05717. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In-context retrieval (ICR) is a retrieval-based form of in-context learning (ICL) in which demonstrations are retrieved from a source database based on similarity to the query, rather than sampled independently. In this work, we formulate ICR as a type of domain adaptation problem, where the source distribution $P$ of the database may differ from the target distribution $Q$ of the test query-label pair. We investigate the performance of ICR under a flexible class of distributional shifts that substantially extends prior work \citep{li2024fine,guo2025retrieval}, and establish theoretical guarantees that quantify the benefits and pitfalls of this learning paradigm. Our theory is verified by experiments on synthetic and language tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05717 — 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 2026-10-06T05:27:06.010Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).