Metraipolis › archive › dc_b15657dc96c8

OptST: Optimizing Semantic Tokenization for LLM-Enhanced Recommendation — arXiv:2611.07523

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07523
License (as archived)
CC0-1.0
Archived
2026-11-06T14:53:11.969Z
SHA-256 of the archived text
378d9e75aaf6f3232ba66e044f2eb21c13839f0f17f446fb05c3a146325bfa57
Stable URL of this page
https://metraipolis.com/documento/dc_b15657dc96c8

How to cite

OptST: Optimizing Semantic Tokenization for LLM-Enhanced Recommendation — arXiv:2611.07523 — arXiv (en), https://arxiv.org/abs/2611.07523 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b15657dc96c8 (Metraipolis archive dc_b15657dc96c8, sha256 378d9e75aaf6f3232ba66e044f2eb21c13839f0f17f446fb05c3a146325bfa57)
BibTeX
@misc{dcb15657dc96c8,
  title = {OptST: Optimizing Semantic Tokenization for LLM-Enhanced Recommendation — arXiv:2611.07523},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07523},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b15657dc96c8; sha256 378d9e75aaf6f3232ba66e044f2eb21c13839f0f17f446fb05c3a146325bfa57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07523. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Semantic information can enrich the identifiers and structured fields used by recommender systems. Semantic tokenization provides a structured representation of this information by converting LLM-derived user profiles into discrete tokens. In the common two-stage pipeline, the tokenizer is trained before the recommender. Its token assignments are then treated as fixed input features during recommendation training. As a result, the downstream recommender can learn how to use the assigned indices, but it cannot revise the semantic partition that produced them. Making this partition task-aware is difficult because nearest-code assignment is discrete, and unconstrained adaptation may also distort the geometry learned during pretraining. Moreover, a fixed token depth exposes the same semantic resolution to every interaction. We thus propose OptST (Optimizing Semantic Tokenization), which makes a pretrained tokenizer responsive to downstream recommendation. To revise token assignments without directly updating the pretrained encoder or base codebooks, OptST learns a low-rank deformation whose drift is limited by an anchor regularizer. Recommendation supervision reaches this transformation through a straight-through estimator, while prediction retains hard nearest-code assignments. Beyond adapting the assignments themselves, OptST selects an interaction-conditioned prefix to control how much residual detail is exposed to the recommender. Experiments on four public datasets show that OptST achieves the highest AUC among conventional and LLM-enhanced baselines. Its improvements also persist across different recommendation backbones. These results establish task-aware semantic tokenization as an effective interface between LLM-derived profiles and downstream recommendation models.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2611.07523 — 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 2026-11-06T14:25:27.639Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).