Metraipolis › archive › dc_eee0b0a1cbca
PACERec: Progressive Adaptation of LLM Item Embeddings with Collaborative Evidence for Recommendation — arXiv:2611.03068
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03068
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:38:06.227Z
- SHA-256 of the archived text
98b17ac5c80e0cfdc62e692123f41a629c5e53e1434050a0f092df5d73d447bc- Stable URL of this page
https://metraipolis.com/documento/dc_eee0b0a1cbca
How to cite
PACERec: Progressive Adaptation of LLM Item Embeddings with Collaborative Evidence for Recommendation — arXiv:2611.03068 — arXiv (en), https://arxiv.org/abs/2611.03068 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eee0b0a1cbca (Metraipolis archive dc_eee0b0a1cbca, sha256 98b17ac5c80e0cfdc62e692123f41a629c5e53e1434050a0f092df5d73d447bc)
BibTeX
@misc{dceee0b0a1cbca,
title = {PACERec: Progressive Adaptation of LLM Item Embeddings with Collaborative Evidence for Recommendation — arXiv:2611.03068},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03068},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eee0b0a1cbca; sha256 98b17ac5c80e0cfdc62e692123f41a629c5e53e1434050a0f092df5d73d447bc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03068. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM) embeddings have been increasingly adopted in sequential recommendation to encode static item attributes and alleviate the limitations of item ID embeddings under sparse interactions. However, these embeddings typically capture only static content similarity while neglecting sequential transitions, and since their adaptation quality relies on sparse per-item updates or global geometric calibration, existing methods still struggle to explicitly transfer preceding interaction contexts from frequent to long-tail items under unevenly distributed behavioral evidence, limiting recommendation effectiveness across the catalog. To address this challenge, we propose PACERec, an ID-free progressive adaptation framework that incorporates preceding interaction contexts into semantic representation adaptation by learning a shared velocity field from items with sufficient interactions via frequency-weighted flow matching. In this way, PACERec progressively guides static LLM embeddings toward collaborative behavioral targets while preserving original item semantics, overcoming sparse per-item updates to effectively generalize sequential transition patterns to long-tail items for both user modeling and candidate scoring. Extensive experiments on three real-world datasets across three sequential backbones demonstrate the superiority of our method over competitive baselines in both overall and long-tail recommendation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.03068 — 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 2026-11-03T10:29:48.921Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).