Metraipolis › archive › dc_604cb79e1a17

LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation — arXiv:2608.03382

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03382
License (as archived)
CC0-1.0
Archived
2026-10-31T12:43:09.979Z
SHA-256 of the archived text
6a4f8d8558f4fa6cd05ff3b0837a7d629a4cb0505db60d82bcd5470c5ee5201b
Stable URL of this page
https://metraipolis.com/documento/dc_604cb79e1a17

How to cite

LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation — arXiv:2608.03382 — arXiv (en), https://arxiv.org/abs/2608.03382 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_604cb79e1a17 (Metraipolis archive dc_604cb79e1a17, sha256 6a4f8d8558f4fa6cd05ff3b0837a7d629a4cb0505db60d82bcd5470c5ee5201b)
BibTeX
@misc{dc604cb79e1a17,
  title = {LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation — arXiv:2608.03382},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03382},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_604cb79e1a17; sha256 6a4f8d8558f4fa6cd05ff3b0837a7d629a4cb0505db60d82bcd5470c5ee5201b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03382. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-armed bandit algorithms, especially Thompson sampling, are widely used in online recommendation. Despite their ability to adapt from online feedback, these methods often suffer from cold-start limitations when newly introduced arms have little or no interaction history. In our setting, the candidate arms are user-generated textual comments, whose semantic content can reveal a title's appeal before sufficient interaction feedback is available. We therefore use large language models (LLMs) to extract semantic signals from comment text and convert them into informative Bayesian priors that warm-start Thompson sampling under sparse early-stage feedback. To account for aggregate segment-level differences in response patterns, we maintain and update posteriors separately for each gender-age segment. In a real-world online A/B/C test, we compare a uniform prior with two LLM-based designs: a Gender Prior for demographic-affinity cues and a Content Prior for title-specific identity cues. The results show that LLM-based priors are most beneficial in sparse-feedback regimes -- with the largest gains emerging once a small amount of interaction evidence has accumulated -- and that prior design leads to distinct funnel-level effects. We further analyze prior-reward alignment and demographic heterogeneity, finding that click-oriented alignment is strongest for the Gender Prior and that treatment effects vary substantially across demographic segments. These findings suggest that LLM-derived priors can serve as a practical warm-start mechanism for text-rich bandit recommendation, while also revealing deployment trade-offs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.LG).
Categorie arXiv: Information Retrieval (cs.IR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.03382 — 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 2026-10-31T12:31:30.411Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).