Metraipolis › archive › dc_dcc9ea90aeca

PDMR: Passage-Driven Multi-ID Document Retrieval — arXiv:2609.08762

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08762
License (as archived)
CC0-1.0
Archived
2026-10-16T15:05:26.751Z
SHA-256 of the archived text
a0f63f63b99ec2df58dc82329d6b7a77ee7c3dbc4ddc99e7ab96128535b7b4f4
Stable URL of this page
https://metraipolis.com/documento/dc_dcc9ea90aeca

How to cite

PDMR: Passage-Driven Multi-ID Document Retrieval — arXiv:2609.08762 — arXiv (en), https://arxiv.org/abs/2609.08762 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcc9ea90aeca (Metraipolis archive dc_dcc9ea90aeca, sha256 a0f63f63b99ec2df58dc82329d6b7a77ee7c3dbc4ddc99e7ab96128535b7b4f4)
BibTeX
@misc{dcdcc9ea90aeca,
  title = {PDMR: Passage-Driven Multi-ID Document Retrieval — arXiv:2609.08762},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08762},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcc9ea90aeca; sha256 a0f63f63b99ec2df58dc82329d6b7a77ee7c3dbc4ddc99e7ab96128535b7b4f4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08762. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative Retrieval (GR) models map queries directly to document identifiers, replacing conventional retrieval over external sparse or dense indexes with autoregressive identifier generation. However, most generative retrieval frameworks rely on a single-identifier assumption, mapping each document to a single target sequence. This forces the model to represent all document content with one sequence. Since documents are often multi-faceted, this can lead to lossy representations and reduced robustness to query variation, where multiple query intents must compete for a single generative access path. In this work, we introduce Passage-Driven Multi-ID Retrieval (PDMR), a generative retrieval framework that represents documents through multiple passage-level identifiers. PDMR segments each document and assigns one identifier to each selected passage, which provides multiple semantic entry points for retrieving the same document. This multi-entry representation allows the model to align queries with specific semantic facets, thereby reducing the dependence on a single document-level target. To address the supervision ambiguity of this one-to-many mapping, we formulate training as a multi-target learning problem and explore an objective function designed to distribute probability mass across multiple valid passage-level identifiers. We evaluate PDMR on NQ320K and MS MARCO Document. On NQ320K, PDMR improves over strong generative and non-generative baselines on Recall@1 and MRR@100. On MS MARCO Document, PDMR achieves the best Recall@1 and MRR@10 among the reported methods, while remaining competitive on Recall@10. Controlled ablations further show that passage-level supervision, identifier design, training-query augmentation, and multi-target learning contribute complementary gains.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.08762 — 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 2026-10-16T14:49:33.965Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).