Metraipolis › archive › dc_fab602cc93c8
Creating an Atomic User Model for Personality-Aware Large Language Model Interaction — arXiv:2609.12086
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12086
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:03:09.346Z
- SHA-256 of the archived text
8a530f0b104529d3af08bf062d155167b55765b25079070c54301dc96a7c96ab- Stable URL of this page
https://metraipolis.com/documento/dc_fab602cc93c8
How to cite
Creating an Atomic User Model for Personality-Aware Large Language Model Interaction — arXiv:2609.12086 — arXiv (en), https://arxiv.org/abs/2609.12086 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fab602cc93c8 (Metraipolis archive dc_fab602cc93c8, sha256 8a530f0b104529d3af08bf062d155167b55765b25079070c54301dc96a7c96ab)
BibTeX
@misc{dcfab602cc93c8,
title = {Creating an Atomic User Model for Personality-Aware Large Language Model Interaction — arXiv:2609.12086},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12086},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fab602cc93c8; sha256 8a530f0b104529d3af08bf062d155167b55765b25079070c54301dc96a7c96ab},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12086. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Assistants built on large language models are expected to write in their users' own voice. Most systems summarise the user's preferences and include the summary in the prompt. This is the wrong way round. Preferences are only the surface of a person and change with the task, while the underlying personality stays the same, so storing preferences alone means relearning the user afresh whenever the task changes. This paper makes four contributions. First, we describe an effect we call personality seepage: the wording of a prompt carries traces of the writer's personality, which the assistant copies without knowing the writer. Second, we propose the Atomic User Model (AUM), a readable profile with a stable identity core surrounded by four layers covering psychological, cognitive, experiential, behavioral, and social details, plus notes on inner conflict and authenticity. Third, instead of inserting the entire profile, we use AUM as a searchable index, in which a task classifier, a selection step, and a budgeted retriever pass along only a few relevant fields. Fourth, we test the pipeline with 16 simulated users, 6 style-sensitive tasks, and 3 seeds. Eight retrieved fields matched the writing quality of the whole profile, while using only 23 percent of the context (211 tokens instead of 915). They scored 0.24 points higher than a plain preference note on a five-point scale. Accuracy in picking a user's own writing from four samples rose from 14.9 to 42.7 percent, where guessing gives 25 percent. Four pre-registered controls showed no effect, so the gain comes from the profile's structure rather than the search method. Personalization helps most for the users for whom a generic assistant imitates them the worst. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.12086 — 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 2026-10-16T02:51:27.856Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).