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

A new arXiv paper (2609.16779v1) presents the first end-to-end approach that enables large language models to perform the complete Analytic Hierarchy Process (AHP) workflow, according to its authors. The study constructs a new annotated AHP benchmark and reports that experiments on real-world decision problems in the legal and higher-education ranking domains significantly improve alignment with expert judgments. The work targets the opacity of LLM internal reasoning, which the authors say is especially critical in high-stakes settings.

arXiv:2609.16779v1 Announce Type: new Abstract: 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.