Metraipolis › archive › dc_c96b71bf5203

AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases — arXiv:2610.32780

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32780
License (as archived)
CC0-1.0
Archived
2026-10-26T19:52:38.578Z
SHA-256 of the archived text
91bc1063af7cb3bf18a598d9d8b69a9cccf721c84588bb4805403562f857a302
Stable URL of this page
https://metraipolis.com/documento/dc_c96b71bf5203

How to cite

AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases — arXiv:2610.32780 — arXiv (en), https://arxiv.org/abs/2610.32780 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c96b71bf5203 (Metraipolis archive dc_c96b71bf5203, sha256 91bc1063af7cb3bf18a598d9d8b69a9cccf721c84588bb4805403562f857a302)
BibTeX
@misc{dcc96b71bf5203,
  title = {AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases — arXiv:2610.32780},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32780},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c96b71bf5203; sha256 91bc1063af7cb3bf18a598d9d8b69a9cccf721c84588bb4805403562f857a302},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32780. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI representation is emerging in digital democracy, assisting in voter emulation and decision-making. Large language models (LLMs) behave differently depending on the model, the prompt context, and the voter information they receive, representing some groups more accurately than others and potentially making the emulation unfair to certain groups. We investigate demographic biases in LLM-emulated electorates: how accurately LLMs represent individual votes, whether some voter groups are represented more accurately than others, and whether AI alignment can reduce these disparities without sacrificing overall accuracy. Using three U.S. presidential elections, we compare a closed-source and an open-source LLM across voters' demographic features and test AI alignment strategies toward fairer voter representation. Removing gender from the voter profile reduces the largest group error of the models by 22-42%, and removing education reduces it by 64%, whereas removing self-reported race increases the mean group error by over 40%, all without lowering accuracy. Common alignment strategies, such as repeated queries or fairness instructions, do not reduce these errors and can double them.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computers and Society (cs.CY) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.32780 — 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 2026-10-26T19:45:33.434Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).