Metraipolis › archive › dc_95da7f3678dc
CrossQ: Task-Aligned Cross-Token Conditional Quantization for Late Interaction Retrieval — arXiv:2608.19204
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19204
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T12:03:27.453Z
- SHA-256 of the archived text
e9ac60954d581a54fef731bbd4130624af3b9c8fd013f9b8d5169495bdebc0d1- Stable URL of this page
https://metraipolis.com/documento/dc_95da7f3678dc
How to cite
CrossQ: Task-Aligned Cross-Token Conditional Quantization for Late Interaction Retrieval — arXiv:2608.19204 — arXiv (en), https://arxiv.org/abs/2608.19204 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_95da7f3678dc (Metraipolis archive dc_95da7f3678dc, sha256 e9ac60954d581a54fef731bbd4130624af3b9c8fd013f9b8d5169495bdebc0d1)
BibTeX
@misc{dc95da7f3678dc,
title = {CrossQ: Task-Aligned Cross-Token Conditional Quantization for Late Interaction Retrieval — arXiv:2608.19204},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19204},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_95da7f3678dc; sha256 e9ac60954d581a54fef731bbd4130624af3b9c8fd013f9b8d5169495bdebc0d1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19204. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Late-interaction retrievers like ColBERT achieve high quality but suffer from large multi-vector indices. Standard compression minimizes token reconstruction error, while ranking depends critically on preserving scores of sparse "winner" tokens. We introduce CrossQ, which adaptively improves effective token fidelity within documents by conditioning token codes on lightweight document context computed at indexing time (but not stored). CrossQ is trained with ranking-aligned objectives that preserve candidate score distributions and protect hard-negative margins. At 2 B/token, CrossQ improves MRR@10 by +0.010 over the strongest strictly footprint-matched quantization baseline and by +0.012 over the strongest candidate-matched system reference. On a nine-dataset BEIR subset, CrossQ improves average nDCG@10 by +0.009 at 4 B/token over the strongest candidate-matched system reference. At 4 B/token, CrossQ achieves 64x raw token-storage reduction, approximately 61x including metadata and approximately 58x under conservative padding/alignment accounting. At 8 B/token, CrossQ with light fine-tuning retains approximately 98% of full-precision ColBERT MRR@10, improving the footprint-quality tradeoff for memory-constrained late-interaction retrieval. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.IR). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2608.19204 — 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 2026-10-18T12:01:23.925Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).