Metraipolis › archive › dc_113381ecefbe

Toward a Theory of Value in AI Alignment — arXiv:2608.10327

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10327
License (as archived)
CC0-1.0
Archived
2026-10-19T06:08:18.534Z
SHA-256 of the archived text
404453fe6d01714884dacadf871e0f7303ca4e069c9289c546cd082227b3d2c8
Stable URL of this page
https://metraipolis.com/documento/dc_113381ecefbe

How to cite

Toward a Theory of Value in AI Alignment — arXiv:2608.10327 — arXiv (en), https://arxiv.org/abs/2608.10327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_113381ecefbe (Metraipolis archive dc_113381ecefbe, sha256 404453fe6d01714884dacadf871e0f7303ca4e069c9289c546cd082227b3d2c8)
BibTeX
@misc{dc113381ecefbe,
  title = {Toward a Theory of Value in AI Alignment — arXiv:2608.10327},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10327},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_113381ecefbe; sha256 404453fe6d01714884dacadf871e0f7303ca4e069c9289c546cd082227b3d2c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Can AI systems be aligned to human values? The popularization of large language models (LLMs) and multi-modal foundation models has seen a rise in harms spanning from toxic speech and hallucinations to AI agents executing unauthorized actions. Within the field of AI safety, these harmful instances are often framed as the alignment problem, or of models being misaligned with human values. Researchers have responded by pursuing applied and theoretical AI value alignment efforts, often without specifying what they mean by human values. How does the field of AI value alignment conceive of human values? How are these conceptions of values technically operationalized and evaluated? What does the emergent theory of value from this field signify for the future of AI? We annotated 94 value alignment research papers to discern their implicit theory of values in AI. The majority do not define values, relying heavily on preferences as a stand in that runs the risk of reducing complex culturally situated concepts down to binary choices. As researchers dispense with using human annotators for model training and evaluation, turning instead to synthetic data and autorater approaches to aligning and evaluating models, we identify the potential to close off alternative methods for contesting and enacting values in foundation models. In making AI value alignments philosophical commitments explicit, we seek to bring great specificity and under explored perspectives in the debate on whether and how AI can address human values.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.10327 — 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 2026-10-19T05:57:28.256Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).