Simulating multiple human perspectives in socio-ecological systems using large language models
career value
195K/year
🤖 AI Summary
This study addresses the challenge of modeling and integrating heterogeneous stakeholder perspectives within social-ecological systems. We propose HoPeS (Holistic Perspective Simulation), a framework centered on large language models as cognitive agents, integrated with an embedded land-use model, role-embodiment protocols, and multi-round simulation scaffolding. HoPeS enables users to dynamically alternate among and synthesize divergent viewpoints within narrative-driven, numerically grounded simulation scenarios. It constitutes the first approach to computationally represent cognitive diversity and support interactive reflective practice, successfully reproducing implementation gaps between policy recommendations and on-the-ground practice, as well as associated affective tensions. Empirical evaluation demonstrates that users significantly improve cross-role understanding through strategic narrative adjustment. Results validate HoPeS’s innovation in bridging the researcher–decision-maker divide and advancing integrative analysis of institutional dynamics and land-use change.
Application Category
📝 Abstract
Understanding socio-ecological systems requires insights from diverse stakeholder perspectives, which are often hard to access. To enable alternative, simulation-based exploration of different stakeholder perspectives, we develop the HoPeS (Human-Oriented Perspective Shifting) modelling framework. HoPeS employs agents powered by large language models (LLMs) to represent various stakeholders; users can step into the agent roles to experience perspectival differences. A simulation protocol serves as a "scaffold" to streamline multiple perspective-taking simulations, supporting users in reflecting on, transitioning between, and integrating across perspectives. A prototype system is developed to demonstrate HoPeS in the context of institutional dynamics and land use change, enabling both narrative-driven and numerical experiments. In an illustrative experiment, a user successively adopts the perspectives of a system observer and a researcher - a role that analyses data from the embedded land use model to inform evidence-based decision-making for other LLM agents representing various institutions. Despite the user's effort to recommend technically sound policies, discrepancies persist between the policy recommendation and implementation due to stakeholders' competing advocacies, mirroring real-world misalignment between researcher and policymaker perspectives. The user's reflection highlights the subjective feelings of frustration and disappointment as a researcher, especially due to the challenge of maintaining political neutrality while attempting to gain political influence. Despite this, the user exhibits high motivation to experiment with alternative narrative framing strategies, suggesting the system's potential in exploring different perspectives. Further system and protocol refinement are likely to enable new forms of interdisciplinary collaboration in socio-ecological simulations.
Problem
Research questions and friction points this paper is trying to address.
Simulating diverse stakeholder perspectives in socio-ecological systems
Exploring perspectival differences using LLM-powered agent roles
Addressing discrepancies between policy recommendations and implementations
Innovation
Methods, ideas, or system contributions that make the work stand out.
LLM-powered agents simulate diverse stakeholder perspectives
Simulation protocol scaffolds multi-perspective exploration
Narrative and numerical experiments enable perspective integration
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
