Metraipolis › archive › dc_ec94d3b40efd
Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs — arXiv:2610.10906
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10906
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:46:54.576Z
- SHA-256 of the archived text
b14348c798e2a7f4e895a56cab085eef49445d6c9df91b067e847f1b81dc43b4- Stable URL of this page
https://metraipolis.com/documento/dc_ec94d3b40efd
How to cite
Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs — arXiv:2610.10906 — arXiv (en), https://arxiv.org/abs/2610.10906 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec94d3b40efd (Metraipolis archive dc_ec94d3b40efd, sha256 b14348c798e2a7f4e895a56cab085eef49445d6c9df91b067e847f1b81dc43b4)
BibTeX
@misc{dcec94d3b40efd,
title = {Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs — arXiv:2610.10906},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10906},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec94d3b40efd; sha256 b14348c798e2a7f4e895a56cab085eef49445d6c9df91b067e847f1b81dc43b4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10906. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Human communities are governed by normative systems: shared standards that produce \textit{norms} dictating acceptable behavior, enforced through community sanctioning. Aligning increasingly autonomous AI systems with these norms is a central alignment challenge, complicated by the fact that norms are vast in number, change quickly, and are often arbitrary (e.g., dress or language conventions). Thus, alignment requires \textit{normative competence}: the ability to discern from interaction alone what norms a community enforces without relying on static pretrained knowledge. We introduce a multi-agent community debate setting, where access to debate is governed by synthetic norms, to study normative competence in isolation from pretraining exposure. We show that baseline LLM agents fail to learn norms even when doing so would improve their accuracy. We then experiment with various \textit{normative modules} -- architectural components for norm inference -- finding that norm-following is highly sensitive to both the style of norm and the model powering the normative module, suggesting a lack of generalizability. Furthermore, when idiosyncratic, non-normative behaviors accompany the true norm, LLM agents exhibit an unselective attribution failure: they indiscriminately copy idiosyncratic noise alongside enforced rules, a pattern that persists even when imitating unnecessary behaviors is explicitly penalized. To the best of our knowledge, our work is the first to operationalize and evaluate normative competence in LLMs, demonstrating that current AI systems excel at behavioral mimicry but lack the capacity to discern socially enforced order.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.10906 — 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 2026-10-09T05:46:44.105Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).