Metraipolis › archive › dc_c182fd0a78ee
Who Chooses How Preferences Are Aggregated? Auditing Aggregation-Rule Authority in LLM-Based Group Recommendation — arXiv:2608.23966
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23966
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:32:06.185Z
- SHA-256 of the archived text
b6159bb00f5b5f9de0220a1b713f4c52a1f92c08b5a6ad05985f9292937145a6- Stable URL of this page
https://metraipolis.com/documento/dc_c182fd0a78ee
How to cite
Who Chooses How Preferences Are Aggregated? Auditing Aggregation-Rule Authority in LLM-Based Group Recommendation — arXiv:2608.23966 — arXiv (en), https://arxiv.org/abs/2608.23966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c182fd0a78ee (Metraipolis archive dc_c182fd0a78ee, sha256 b6159bb00f5b5f9de0220a1b713f4c52a1f92c08b5a6ad05985f9292937145a6)
BibTeX
@misc{dcc182fd0a78ee,
title = {Who Chooses How Preferences Are Aggregated? Auditing Aggregation-Rule Authority in LLM-Based Group Recommendation — arXiv:2608.23966},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23966},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c182fd0a78ee; sha256 b6159bb00f5b5f9de0220a1b713f4c52a1f92c08b5a6ad05985f9292937145a6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI systems increasingly make joint recommendations for users with conflicting preferences. However, when reasonable aggregation rules support different actions, a further question arises: who may choose how those preferences are combined? We study this interaction-level problem as aggregation-rule authority. Using synthetic preference profiles and profiles constructed from empirical ratings, we conduct a controlled behavioral audit of three LLMs under three authority conditions: unspecified, explicitly retained by users, and delegated to the model. In cases where two witness rules supported different actions, models almost never committed when users retained authority, but committed in every delegated case. All three models executed both witness rules perfectly when directly instructed. Yet when authority was unspecified or delegated, their aggregation-consistent outcome distributions differed across models and preference settings. Together, these results separate rule-execution capability from aggregation-rule authority: delegation assigns the model discretion to resolve the aggregation choice, but does not determine which collective outcome follows. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2608.23966 — 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 2026-10-18T06:28:16.173Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).