Theory Discovery in Social Networks: Automating ERGM Specification with Large Language Models

2026-03-04

AI Summary

This study addresses a critical bottleneck in the empirical validation of qualitative social theories: the reliance on expert knowledge to translate theoretical constructs into estimable Exponential Random Graph Model (ERGM) specifications. To overcome this challenge, the authors propose Forge, a novel framework that integrates large language models with statistical safeguards to automatically generate and iteratively refine ERGM candidate specifications from natural language descriptions of social contexts and observed network data. By incorporating stability constraints and goodness-of-fit diagnostics, Forge ensures both model feasibility and adequacy. Evaluated on 12 benchmark social networks, Forge achieved convergence in 10 cases, with 9 attaining optimal likelihood fit and meeting sufficiency thresholds. This approach substantially reduces the manual effort required for ERGM specification, establishing an automated bridge from abstract social theory to testable statistical models.

Technology Category

• Knowledge Representation and Reasoning: Qualitative Reasoning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Understanding how social networks form, whether through reciprocity, shared attributes, or triadic closure, is central to computational social science. Exponential Random Graph Models (ERGMs) offer a principled framework for testing such formation theories, but translating qualitative social hypotheses into stable statistical specifications remains a significant barrier, requiring expertise in both network theory and model estimation. We present Forge (Formation-Oriented Reasoning with Guarded ERGMs), a framework that uses large language models to automate this translation. Given a network and an informal description of the social context, Forge proposes candidate formation mechanisms, validates them against feasibility and stability constraints, and iteratively refines specifications using goodness-of-fit diagnostics. Evaluation across twelve benchmark networks spanning schools, organizations, and online communication shows that Forge converges in 10 of 12 cases, and conditional on convergence it achieves the best likelihood-based fit in 9 of 10 while meeting adequacy thresholds. By combining LLM-based proposals with statistical guardrails, Forge reduces the manual effort required for ERGM specification.

Problem

• Theory Discovery
• Social Networks
• Exponential Random Graph Models
• ERGM Specification
• Statistical Modeling

Innovation

• Exponential Random Graph Models
• Large Language Models
• Automated Model Specification
• Social Network Formation
• Statistical Guardrails