Metraipolis › archive › dc_ce376ac89d49
Hypotheses-Guided Self Distillation for Continual Personalization — arXiv:2609.00251
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00251
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:31:45.657Z
- SHA-256 of the archived text
6ed637e2c8cefb49494d830a9853d370f38b1d0edc897967e3c3392e643c92ba- Stable URL of this page
https://metraipolis.com/documento/dc_ce376ac89d49
How to cite
Hypotheses-Guided Self Distillation for Continual Personalization — arXiv:2609.00251 — arXiv (en), https://arxiv.org/abs/2609.00251 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce376ac89d49 (Metraipolis archive dc_ce376ac89d49, sha256 6ed637e2c8cefb49494d830a9853d370f38b1d0edc897967e3c3392e643c92ba)
BibTeX
@misc{dcce376ac89d49,
title = {Hypotheses-Guided Self Distillation for Continual Personalization — arXiv:2609.00251},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00251},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce376ac89d49; sha256 6ed637e2c8cefb49494d830a9853d370f38b1d0edc897967e3c3392e643c92ba},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00251. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As people increasingly interact with LLM assistants in daily life, continually adapting to individual preferences has become essential for effective long-term interactions. However, user preferences are rarely stated in full, and instead emerge through heterogeneous, latent, and noisy signals, with existing methods relying on raw interaction histories or costly reward-based optimization to manage personalization. We introduce HypReflect, a reliable, scalable framework for continual personalization that infers explicit, uncertainty-aware preference hypotheses from diverse user signals, reflectively refines them as new evidence accumulates, and incorporates the resulting user model through hypotheses-guided self-distillation. Experiments across three personalization settings: online personalization, multi-session interactions, and implicit behavioral signals, show that HypReflect outperforms a range of baselines, including raw-history and incremental-update methods. We further demonstrate strong generalization to unseen users and cross-domain settings, along with stability across context budgets, reusable hypotheses, and more focused personalization. These results suggest a step towards reliable and scalable continual personalization through explicit, revisable user preference hypotheses. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.00251 — 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 2026-10-17T06:15:12.577Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).