Metraipolis › archive › dc_dda458743f4e

Search-Aware On-Policy Self-Distillation with Sibling Alignment for Generative Recommendation — arXiv:2611.01568

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01568
License (as archived)
CC0-1.0
Archived
2026-11-03T10:56:45.808Z
SHA-256 of the archived text
5bb84cbdeb76939b02e792cc7aa0a7e68380dc1c82749166d7fda4051289e0b7
Stable URL of this page
https://metraipolis.com/documento/dc_dda458743f4e

How to cite

Search-Aware On-Policy Self-Distillation with Sibling Alignment for Generative Recommendation — arXiv:2611.01568 — arXiv (en), https://arxiv.org/abs/2611.01568 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dda458743f4e (Metraipolis archive dc_dda458743f4e, sha256 5bb84cbdeb76939b02e792cc7aa0a7e68380dc1c82749166d7fda4051289e0b7)
BibTeX
@misc{dcdda458743f4e,
  title = {Search-Aware On-Policy Self-Distillation with Sibling Alignment for Generative Recommendation — arXiv:2611.01568},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01568},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dda458743f4e; sha256 5bb84cbdeb76939b02e792cc7aa0a7e68380dc1c82749166d7fda4051289e0b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01568. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative recommendation retrieves items by autoregressively generating semantic IDs, typically via beam search. On-policy self-distillation (OPSD) enhances training supervision by transferring privileged self-teacher knowledge at student-generated states. However, beam-search retention depends on competition among prefixes: visited states differ in importance, and initially reliable decisions may approach the pruning boundary as training evolves. Moreover, conventional distribution matching couples target-token confidence with preferences among competing continuations, potentially weakening relational supervision when the self-teacher strongly favors the target. To address these challenges, we propose Search-Aware On-Policy Self-Distillation (SA-OPSD), a framework that transfers privileged self-teacher knowledge to the states visited during the student's own beam search. Specifically, we introduce Evolving-Boundary Sampling, which prioritizes search-critical states by considering both current pruning-boundary proximity and initial-reference retention-margin decline under a controlled distillation budget. Furthermore, we develop Confidence-Decoupled Branch Distillation, which separates target-probability calibration from informative sibling relations to better preserve the teacher's preferences among competing branches. Experiments on Industrial, Office, and Instruments demonstrate strong performance for SA-OPSD.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01568 — 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 2026-11-03T10:49:38.568Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).