Metraipolis › archive › dc_288b97348ccc
Adaptive Personalization Under Preference Epistemic Uncertainty — arXiv:2610.40930
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40930
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:05:21.109Z
- SHA-256 of the archived text
12d574c1b4b1f7218fe2939a197780b05425b26c294e532bbc1468fd6b0dadb4- Stable URL of this page
https://metraipolis.com/documento/dc_288b97348ccc
How to cite
Adaptive Personalization Under Preference Epistemic Uncertainty — arXiv:2610.40930 — arXiv (en), https://arxiv.org/abs/2610.40930 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_288b97348ccc (Metraipolis archive dc_288b97348ccc, sha256 12d574c1b4b1f7218fe2939a197780b05425b26c294e532bbc1468fd6b0dadb4)
BibTeX
@misc{dc288b97348ccc,
title = {Adaptive Personalization Under Preference Epistemic Uncertainty — arXiv:2610.40930},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40930},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_288b97348ccc; sha256 12d574c1b4b1f7218fe2939a197780b05425b26c294e532bbc1468fd6b0dadb4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40930. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Human preferences change over time: an established preference may remain valid over time, become uncertain as context shifts, or be explicitly revised. Effective personalization requires conversational AI to adapt its response strategy to evolving preferences rather than relying on passive memory retrieval. We formalize this capability as adaptive personalization under epistemic uncertainty. A human preference study further confirms that people favor state-contingent response strategies as preference uncertainty changes. To evaluate whether language models mirror this adaptation, we create a multilingual benchmark spanning 250 personas, 5 languages, and 25K conversational turns that decouples strategy selection from response execution. Across eight closed- and open-weight models, we uncover a recognition-generation gap: models reliably identify appropriate strategies when selecting among candidate options, but collapse during open-ended generation, suffering a 35-46% drop in strategy calibration. Crucially, this failure is systematic: models default to exploit-first behavior, over-relying on existing preferences regardless of preference epistemic uncertainty. We show this failure is addressable: while prompting interventions fail, targeted training that supervises models' internal strategy representations toward state-conditional human preferences narrows the user acceptability generalization gap by a third on out-of-distribution personas and conversational styles. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.40930 — 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 2026-11-03T07:59:53.578Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).