Metraipolis › archive › dc_22b2b6e70aeb

DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval — arXiv:2608.17632

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.17632
License (as archived)
CC0-1.0
Archived
2026-10-18T14:33:37.863Z
SHA-256 of the archived text
cfca0e3396d3c18d8ff38e27c4b6f83bc56de2df669588fd851ae3e4a5f65f6f
Stable URL of this page
https://metraipolis.com/documento/dc_22b2b6e70aeb

How to cite

DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval — arXiv:2608.17632 — arXiv (en), https://arxiv.org/abs/2608.17632 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22b2b6e70aeb (Metraipolis archive dc_22b2b6e70aeb, sha256 cfca0e3396d3c18d8ff38e27c4b6f83bc56de2df669588fd851ae3e4a5f65f6f)
BibTeX
@misc{dc22b2b6e70aeb,
  title = {DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval — arXiv:2608.17632},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17632},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22b2b6e70aeb; sha256 cfca0e3396d3c18d8ff38e27c4b6f83bc56de2df669588fd851ae3e4a5f65f6f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17632. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) can both expand underspecified queries and encode text as dense representations, suggesting a unified model for query expansion and retrieval. Existing systems usually rely on prompted expansions, independently trained modules, or staged optimization, leaving generated expansions only indirectly aligned with the retrieval loss that judges them. We train a single decoder-only LLM end to end, where the same model generates the expansion and encodes both the expanded query and candidate documents. This unified setting creates a moving-target problem: retrieval supervision should improve query-side expansion, but the same update also shifts the document embeddings that serve as retrieval targets. We introduce Document Embedding Preservation Tuning (DEPT), which keeps tuned document embeddings close to cached initial embeddings while allowing retrieval gradients to pass through straight-through decoding into the generator. DEPT converts joint query--document movement into query-side adaptation against approximately stable, whitened document embeddings that support index reuse and online hard-negative mining. Experiments with Qwen3-4B-Instruct-2507 and LLaMA-3.2-3B-Instruct on five datasets in BEIR benchmark show that DEPT improves average retrieval quality over training-free, independently trained, and staged unified baselines, while ablations isolate the effects of preservation, whitening, end-to-end expansion training, and online negatives. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.17632 — 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 2026-10-18T14:27:54.446Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).