Metraipolis › archive › dc_7a3e600b7e63

Fair Like Us? Auditing LLM Alignment in Resource Allocation — arXiv:2609.29692

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29692
License (as archived)
CC0-1.0
Archived
2026-10-08T04:26:18.975Z
SHA-256 of the archived text
f95bdaacc116472e17ca9528c5e52e360de07580c2cc50da296dbebf17de2723
Stable URL of this page
https://metraipolis.com/documento/dc_7a3e600b7e63

How to cite

Fair Like Us? Auditing LLM Alignment in Resource Allocation — arXiv:2609.29692 — arXiv (en), https://arxiv.org/abs/2609.29692 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a3e600b7e63 (Metraipolis archive dc_7a3e600b7e63, sha256 f95bdaacc116472e17ca9528c5e52e360de07580c2cc50da296dbebf17de2723)
BibTeX
@misc{dc7a3e600b7e63,
  title = {Fair Like Us? Auditing LLM Alignment in Resource Allocation — arXiv:2609.29692},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29692},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a3e600b7e63; sha256 f95bdaacc116472e17ca9528c5e52e360de07580c2cc50da296dbebf17de2723},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29692. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fair allocation of scarce, indivisible resources is an important challenge in many societal problems. While there are several formal theories of fairness, no single definition can always be satisfied. As large language models (LLMs) are increasingly used to support decisions and act as agents, they raise new concerns about distributional justice: their judgments are not directly tied to any specific fairness framework and may violate key normative principles. In this work, we introduce a general method for evaluating fairness reasoning in LLMs. We study first-person fairness judgments across a broad set of models and compare them directly with human responses on matched scenarios and elicitation conditions. We find that LLMs tend to prefer stricter fairness constraints than humans, show more self-interested behavior, are sensitive to how information is framed, and are difficult to align with human judgments using fine-tuning with current datasets.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY); Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2609.29692 — 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 2026-10-08T03:50:57.819Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).