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

TL;DR

This paper introduces Forge, a framework leveraging large language models to automate the translation of social hypotheses into ERGM specifications, significantly reducing manual effort and improving model fitting accuracy in social network analysis.

Contribution

Forge automates ERGM specification from informal social hypotheses using LLMs, incorporating validation and iterative refinement to enhance model stability and fit.

Findings

Forge converges in 10 of 12 benchmark cases.

Achieves best likelihood fit in 9 of 10 converged cases.

Reduces manual effort in ERGM specification.

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.