Metraipolis › archive › dc_cd95f3d82db1

Contextual Value Alignment via Multilayer Combinatorial Fusion — arXiv:2608.07642

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07642
License (as archived)
CC0-1.0
Archived
2026-10-19T06:49:29.109Z
SHA-256 of the archived text
8c6f3decc2b24d64fe5c6ba3ed3635e0f16ae28962cd987fdc9b549e998c55db
Stable URL of this page
https://metraipolis.com/documento/dc_cd95f3d82db1

How to cite

Contextual Value Alignment via Multilayer Combinatorial Fusion — arXiv:2608.07642 — arXiv (en), https://arxiv.org/abs/2608.07642 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd95f3d82db1 (Metraipolis archive dc_cd95f3d82db1, sha256 8c6f3decc2b24d64fe5c6ba3ed3635e0f16ae28962cd987fdc9b549e998c55db)
BibTeX
@misc{dccd95f3d82db1,
  title = {Contextual Value Alignment via Multilayer Combinatorial Fusion — arXiv:2608.07642},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07642},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd95f3d82db1; sha256 8c6f3decc2b24d64fe5c6ba3ed3635e0f16ae28962cd987fdc9b549e998c55db},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07642. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI. While existing approaches such as RLHF, CAI, and their variants have achieved promising results, they often rely on a single-agent framework and a unified reward system. This limits their ability to capture ethical pluralism, adapt to diverse moral contexts, and reflect the dynamics of multi-agent moral reasoning. In this work, we propose a framework that utilizes multilayer combinatorial fusion for contextual value alignment (MCF-CVA). At the first layer of the framework, it instantiates multiple moral agents, each fine-tuned to represent a distinctive value. Their outputs are then expanded combinatorially using both score- and rank-combinations as well as average and weighted aggregations. These combined models are then reduced to the same number of initial moral agents. This expansion and reduction (EAR) process continues for multi-layers until a stopping criterion is reached. The MCF-CVA framework leverages cognitive diversity between agents to mitigate conflicts and redundancies across multiple agents, producing responses that better reflect contextual human values. The framework using the EAR algorithm is performed on the dual architecture of Euclidean score space and Kemeny rank space. Empirical evaluations demonstrated that the proposed framework outperforms single-agent baselines, multi-agent single-layer results, and previous aggregation approaches on standard metrics, showing that the MCF-CVA framework provides a robust and effective mechanism for advancing contextual value alignment in LLMs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.07642 — 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 2026-10-19T06:45:31.701Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).