Metraipolis › archive › dc_8d4f2ba8bee9

Persona Learning from Feedback for Personalized AI Assistants — arXiv:2610.38561

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38561
License (as archived)
CC0-1.0
Archived
2026-10-31T06:12:47.985Z
SHA-256 of the archived text
97a74c36990e7a21e90a41abf7a36c2410f8705d5abca9adf97580494433e1a4
Stable URL of this page
https://metraipolis.com/documento/dc_8d4f2ba8bee9

How to cite

Persona Learning from Feedback for Personalized AI Assistants — arXiv:2610.38561 — arXiv (en), https://arxiv.org/abs/2610.38561 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d4f2ba8bee9 (Metraipolis archive dc_8d4f2ba8bee9, sha256 97a74c36990e7a21e90a41abf7a36c2410f8705d5abca9adf97580494433e1a4)
BibTeX
@misc{dc8d4f2ba8bee9,
  title = {Persona Learning from Feedback for Personalized AI Assistants — arXiv:2610.38561},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38561},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d4f2ba8bee9; sha256 97a74c36990e7a21e90a41abf7a36c2410f8705d5abca9adf97580494433e1a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38561. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Personalizing AI assistants requires adapting their behavior to users' preferences and task contexts. Existing work elicits assistant personas through persona prompting or finetuning on persona-conditioned generations. However, persona descriptions alone do not identify what to change or preserve in a particular response, or which behaviors suit the current request. We introduce $\textit{Persona Learning from Feedback (PLF)}$, a framework that learns reusable, preference-grounded assistant personas as independent LoRA adapters on a shared frozen backbone. During training, a frozen self-teacher conditions on persona specifications and response-specific feedback to provide token-level supervision on each adapter's own generated prefixes. A feedback gate focuses corrective updates on responses judged to need improvement. At deployment, a supervised router uses the request or dialogue to select a single adapter or a fixed composition, without user-specific finetuning. We evaluate PLF on single-turn personalization with model-generated critiques and multi-turn tutoring with simulated students' reactions. Across both settings, PLF improves model-judged preference fit over fixed-persona policies and strong baselines including persona prompting and persona distillation, demonstrating how feedback-trained behaviors can be reused for adaptive assistant personalization without degrading general capabilities.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.38561 — 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 2026-10-31T06:07:08.662Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).