Reproduce “The Human-AI Hybrid Delphi Model: A Structured Framework for Context-Rich, Expert Consensus in Complex Domains” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Cathy Speed, Ahmed A. Metwally

The Human–AI Hybrid Delphi (HAH-Delphi) model integrates generative AI (Gemini 2.5 Pro) with small panels of senior human experts and structured facilitation to develop nuanced, context-rich expert consensus. This approach demonstrated 95% alignment with historical consensus and achieved thematic saturation with compact expert panels, enhancing the efficiency and quality of consensus generation.

Key insights

  • Generative AI can reliably replicate historical consensus and serve as a transparent, evidence-grounded benchmark for foundational knowledge.
  • Small panels of senior human experts are sufficient to achieve thematic saturation and provide rich, nuanced, context-sensitive guidance when augmented by AI.
  • Human experts offer unique experiential, pragmatic, and temporal/phased reasoning that complements AI's evidence-based synthesis.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.