Metraipolis › archive › dc_5fd6e4151fc3

Integrating the Analytic Hierarchy Process with Large Language Models for Transparent Multi-Criteria Decision-Making — arXiv:2609.16779

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16779
License (as archived)
CC0-1.0
Archived
2026-10-15T18:32:13.188Z
SHA-256 of the archived text
9c678562c660f444feedbdd0ca2820518bec9cb9e2b8d0b2b5cdc5c8d526eaf6
Stable URL of this page
https://metraipolis.com/documento/dc_5fd6e4151fc3

How to cite

Integrating the Analytic Hierarchy Process with Large Language Models for Transparent Multi-Criteria Decision-Making — arXiv:2609.16779 — arXiv (en), https://arxiv.org/abs/2609.16779 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5fd6e4151fc3 (Metraipolis archive dc_5fd6e4151fc3, sha256 9c678562c660f444feedbdd0ca2820518bec9cb9e2b8d0b2b5cdc5c8d526eaf6)
BibTeX
@misc{dc5fd6e4151fc3,
  title = {Integrating the Analytic Hierarchy Process with Large Language Models for Transparent Multi-Criteria Decision-Making — arXiv:2609.16779},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16779},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5fd6e4151fc3; sha256 9c678562c660f444feedbdd0ca2820518bec9cb9e2b8d0b2b5cdc5c8d526eaf6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16779. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLMs are increasingly employed in a wide range of decision-making tasks. However, the opacity of their internal reasoning makes it difficult to validate or interpret their outputs, and the need for interpretability becomes especially critical in high-stakes settings. This study examines the decision-making capabilities of LLMs through the Analytic Hierarchy Process (AHP), a classical and widely used multicriteria decision-making framework. We construct a new annotated benchmark based on AHP and propose the first end-to-end approach that enables LLMs to perform the complete AHP workflow. Experiments in real-world decision problems in the legal and higher-education ranking domains show that our method significantly improves alignment with expert judgments.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.16779 — 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 2026-10-15T18:03:09.473Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).