Metraipolis › archive › dc_6bfc12564cb3

HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization — arXiv:2609.09835

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09835
License (as archived)
CC0-1.0
Archived
2026-10-16T07:53:21.301Z
SHA-256 of the archived text
023d54cfd4afa35c18581e6dc8bc188b4d854156c84a943a2298252538b6a21f
Stable URL of this page
https://metraipolis.com/documento/dc_6bfc12564cb3

How to cite

HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization — arXiv:2609.09835 — arXiv (en), https://arxiv.org/abs/2609.09835 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6bfc12564cb3 (Metraipolis archive dc_6bfc12564cb3, sha256 023d54cfd4afa35c18581e6dc8bc188b4d854156c84a943a2298252538b6a21f)
BibTeX
@misc{dc6bfc12564cb3,
  title = {HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization — arXiv:2609.09835},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09835},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6bfc12564cb3; sha256 023d54cfd4afa35c18581e6dc8bc188b4d854156c84a943a2298252538b6a21f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09835. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Personalized language models aim to adapt responses to individual users, whose preferences are often latent and revealed gradually through interaction. Existing training-free methods rely on stored histories or retrieved memories, but they often struggle to reconcile long- term preferences with short-term topic-specific needs. To address this issue, we propose HyperTrace, a training-free framework that formulates online personalization as latent preference tracing. HyperTrace maintains interpretable natural-language hypotheses over short-term intent and long-term preferences, and updates them through an SMC-style reweight process using an LLM-based surrogate choice model. By updating these hypotheses across turns and sessions, HyperTrace enables personalization without parameter updates. Experiments on PRISM and PersonaMem-v2 show that HyperTrace improves response alignment, preference prediction, and profile consistency over strong online baselines, demonstrating the effectiveness of tracing latent user preferences for robust personalization. Code and scripts are available in the repository: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.09835 — 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 2026-10-16T07:24:00.901Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).