Reproduce “Using Collective Dialogues and AI to Find Common Ground Between Israeli and Palestinian Peacebuilders” 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

Andrew Konya, Luke Thorburn, Wasim Almasri, Oded Adomi Leshem, Ariel D. Procaccia, Lisa Schirch, Michiel A. Bakker

An AI-assisted deliberative process, integrating online collective dialogues, bridging-based ranking, and large language models, was used to find common ground between Israeli and Palestinian peacebuilders. This methodology generated 10 collective statements with inter-group agreement between 84% and 96%, including demands to world leaders and messages to regional residents, even amidst heightened conflict.

Key insights

  • Despite deep divisions, a mutual alignment of "red lines" and several coarse-grained shared values (e.g., peace, equality, human life) and future visions were identified across Israeli and Palestinian uninational groups.
  • The anonymity of the online dialogue platform, combined with transparent AI use and human expert validation, fostered trust and enabled participants to express views more openly.
  • The recursive, AI-assisted deliberative process successfully produced highly agreed-upon actionable statements even in a high-stakes, active conflict environment, challenging assumptions about AI's role in such contexts.

Summary by alphaXiv.

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