SocialFiVis: A Visual Analytics Sandbox for LLM-Grounded Multi-Agent Simulation in Social Finance
Authors
Yi-Fan Cao (Hong Kong University of Science and Technology), Qing Shi (The Hong Kong University of Science and Technology (Guangzhou)), Liangwei Wang (The Hong Kong University of Science and Technology (Guangzhou)), Leo Yu-Ho Lo (The Hong Kong University of Science and Technology), Lin Chen (Northeastern University), Yuzi Han (HKUST), Yang Wang (The University of Hong Kong), Kani Chen (Hong Kong University of Science and Technology)
Presentation
- Session
- My followers need to know about this!
- Time
- Thursday, Nov 12, 10:12 – 10:24 (US/Eastern) · session 10:00 – 11:30
- Location
- Hall America center
Keywords
LLM-grounded agent simulation, SocialFi, counterfactual reasoning, digital commons governance.
Abstract
The emergence of social finance (SocialFi) transforms online communities into complex socio-economic systems. Within these spaces, collective decisions shape a “digital commons” characterized by social capital (e.g., community trust) and financial health (e.g., market liquidity). Governing such hybrid ecosystems is challenging because real-world interventions are costly and irreversible. While counterfactual simulation is essential for exploring alternative governance strategies, existing approaches fail to capture the non-linear interplay between governance rules, individual behaviors, and emergent economic outcomes. To systematically unpack this complexity, we operationalize the Institutional Analysis and Development (IAD) framework as our theoretical foundation, synthesizing prior literature with insights from formative expert interviews. Built on this framework, we present SocialFiVis, an IAD-embedded visual analytics sandbox. It introduces a robust model to quantify the dual-track digital commons, coupled with a two-phase simulation engine. This engine combines LLM-derived personas with a mechanism-guided Perception–Reasoning–Action (PRA) runtime to simulate heterogeneous, context-aware agents empirically grounded in the retained messaging cohort. A hierarchical multi-view interface with interpretable reasoning pathways enables community operators to explore counterfactual policies and trace system-level outcomes back to individual behavioral rationales. We evaluate SocialFiVis through two case studies, a user study, and follow-up interviews. Results demonstrate that SocialFiVis supports fine-grained behavioral attribution and helps explain emergent phenomena such as the structural decoupling of social capital and the resilience of messaging members under localized governance shocks.
For Practitioners
This paper would be of interest to SocialFi and Web3 community operators and managers, DAO and NFT governance teams, fintech and product analysts, data scientists, and simulation researchers. Practitioners can apply the paper's framework to jointly monitor social and financial community health, explore governance interventions before deploying them in communities, and trace aggregate outcomes back to heterogeneous member personas and the behavioral rationales behind them.