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

2025-03-03

AI Summary

This study investigates the feasibility of AI-assisted approaches to mitigate polarization and foster consensus among Israeli and Palestinian peacebuilders in real-world, high-tension post-conflict settings. Method: From April to July 2024, in collaboration with the Middle East Peace Alliance, we deployed at scale—within an authentic post-conflict context—an LLM-augmented iterative collective dialogue framework. Grounded in social choice theory and the “bridging principle,” the framework integrated a novel bridging-ranking algorithm and a structured multi-round deliberation protocol, engaging Jewish Israelis, Arab citizens of Israel, and Palestinians from the West Bank and Gaza. Contribution/Results: The intervention achieved triple integration of theory, technology, and practice. It yielded multiple jointly authored declarations and unified policy appeals addressed to global leaders, each endorsed by ≥84% of participants across all groups. These outcomes provide empirical validation of AI’s efficacy and scalability in cross-group peacebuilding.

Technology Category

• Humans and AI: Voting
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• 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: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

A growing body of work has shown that AI-assisted methods -- leveraging large language models (LLMs), social choice methods, and collective dialogues -- can help reduce polarization and foster common ground in controlled lab settings. But what can these approaches contribute in real-world contexts? We present a case study applying these techniques to find common ground between Israeli and Palestinian peacebuilders in the period following October 7th, 2023. From April to July 2024 an iterative deliberative process combining LLMs, bridging-based ranking, and collective dialogues was conducted in partnership with the Alliance for Middle East Peace. More than 100 civil society peacebuilders participated including Israeli Jews, Palestinian citizens of Israel, and Palestinians from the West Bank and Gaza. The process culminated in a set of collective statements, including joint demands to world leaders, with at least 84% agreement from participants on each side. In this paper we review the mechanics and implementation of the process, discuss results and learnings, and highlight open problems that warrant future work.

Problem

• AI-assisted methods reduce polarization in real-world conflicts.
• Finding common ground between Israeli and Palestinian peacebuilders.
• Iterative process combining LLMs, ranking, and collective dialogues.

Innovation

• AI-assisted methods reduce polarization effectively.
• Combines LLMs, social choice, collective dialogues.
• Facilitates common ground in real-world conflicts.