Metraipolis › archive › dc_7bedaa260d4e

Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation — arXiv:2609.15094

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.15094
License (as archived): CC0-1.0
Archived: 2026-10-15T22:53:37.118Z
SHA-256 of the archived text: 695386882522e583ff5399c3cfd682e739c339464d806acf750d7e4411c3f983
Stable URL of this page: https://metraipolis.com/documento/dc_7bedaa260d4e

How to cite

Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation — arXiv:2609.15094 — arXiv (en), https://arxiv.org/abs/2609.15094 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7bedaa260d4e (Metraipolis archive dc_7bedaa260d4e, sha256 695386882522e583ff5399c3cfd682e739c339464d806acf750d7e4411c3f983)

BibTeX

@misc{dc7bedaa260d4e,
  title = {Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation — arXiv:2609.15094},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15094},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7bedaa260d4e; sha256 695386882522e583ff5399c3cfd682e739c339464d806acf750d7e4411c3f983},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15094. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In industrial recommendation feeds, presenting a static headline for an item often fails to satisfy the diverse, multimodal interests of the user population, particularly suppressing the needs of long-tail audiences. While Large Language Models (LLMs) have been integrated into recommendation for content understanding or ranking, directly optimizing them to output a single best headline typically leads to mode collapse---converging to generic patterns that satisfy average tastes but miss specific latent intents. To bridge this gap, we introduce GESE (Generate to Explore, Select to Exploit), a framework operating at the system's presentation layer that decouples personalization into generative exploration and selective exploitation. First, we treat the LLM as a probabilistic explorer, utilizing Group Sequence Policy Optimization (GSPO) with a hierarchical reward mechanism to generate a candidate set that maximizes the semantic coverage of potential user interests. Subsequently, a lightweight, real-time feedback-aware selector acts as the exploiter, identifying the optimal realization from the candidate pool based on instant contextual signals. Extensive deployment on a commercial platform with over 100 million daily active users demonstrates that GESE significantly outperforms state-of-the-art baselines, achieving a 2.57% lift in CTR and 0.87% in dwell time. These results validate that decoupling diversity-oriented generation from precision-oriented selection offers a robust blueprint for aligning generative AI with dynamic user utility.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.15094 — 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 2026-10-15T22:29:03.803Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).