The Ethical Compass of the Machine: Evaluating Large Language Models for Decision Support in Construction Project Management

2025-09-02

AI Summary

This study investigates the feasibility and reliability of large language models (LLMs) as ethical decision support tools in high-risk, morally sensitive contexts within construction project management. Method: A mixed-methods approach was employed: (1) performance evaluation of LLMs across 12 real-world ethical scenarios; (2) development and validation of EDSAC—a reusable Ethical Decision Support Assessment Framework; and (3) semi-structured interviews with 12 domain experts. Contribution/Results: LLMs demonstrate moderate competence in structured tasks such as legal compliance but exhibit critical deficiencies in contextual understanding, accountability attribution, and reasoning transparency. Experts uniformly reject autonomous LLM decision-making. This work constitutes the first empirical assessment of LLMs’ ethical reasoning capabilities in the construction domain. It introduces the EDSAC framework and establishes “human-supervised human–AI collaboration” as the optimal current deployment paradigm for ethical decision support in construction management.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

The integration of Artificial Intelligence (AI) into construction project management (CPM) is accelerating, with Large Language Models (LLMs) emerging as accessible decision-support tools. This study aims to critically evaluate the ethical viability and reliability of LLMs when applied to the ethically sensitive, high-risk decision-making contexts inherent in CPM. A mixed-methods research design was employed, involving the quantitative performance testing of two leading LLMs against twelve real-world ethical scenarios using a novel Ethical Decision Support Assessment Checklist (EDSAC), and qualitative analysis of semi-structured interviews with 12 industry experts to capture professional perceptions. The findings reveal that while LLMs demonstrate adequate performance in structured domains such as legal compliance, they exhibit significant deficiencies in handling contextual nuance, ensuring accountability, and providing transparent reasoning. Stakeholders expressed considerable reservations regarding the autonomous use of AI for ethical judgments, strongly advocating for robust human-in-the-loop oversight. To our knowledge, this is one of the first studies to empirically test the ethical reasoning of LLMs within the construction domain. It introduces the EDSAC framework as a replicable methodology and provides actionable recommendations, emphasising that LLMs are currently best positioned as decision-support aids rather than autonomous ethical agents.

Problem

• Evaluating ethical viability of LLMs in construction management
• Assessing LLM reliability for high-risk ethical decision-making
• Testing LLM performance in contextual ethical reasoning scenarios

Innovation

• Evaluating LLMs with ethical scenarios checklist
• Mixed-methods testing with expert interviews
• Proposing human-in-the-loop oversight framework