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

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.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-03-04

• Fields of study

  Sociology, Computer Science, Mathematics

• Identifiers
  arXiv 2603.04306
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• LLMs generate structurally realistic social networks but overestimate political homophily

  2024cited by this paper
• Network formation and dynamics among multi-LLMs

  2024cited by this paper
• Large language models recover scientific collaboration networks from text

  2024cited by this paper
• Generative Agents: Interactive Simulacra of Human Behavior

  2023cited by this paper
• Stochastic step-wise feature selection for Exponential Random Graph Models (ERGMs)

  2023cited by this paper
• Complex network analysis to understand trading partnership in French swine production

  2022cited by this paper
• Network data

  2019cited by this paper
• Markov Graphs

  2018cited by this paper
• Exponential Random Graph Models for Social Networks: Theory, Methods, and Applications

  2014influential reference
• Exponential random graph models for multilevel networks

  2013cited by this paper
• Statistical Mechanics of Networks: Estimation and Uncertainty Forthcoming: Physica A

  2012cited by this paper
• Instability, Sensitivity, and Degeneracy of Discrete Exponential Families

  2011influential reference
• Exponential-family random graph models for valued networks.

  2011cited by this paper
• Inferential Network Analysis with Exponential Random Graph Models

  2011cited by this paper
• Bayesian inference for exponential random graph models

  2010cited by this paper
• Concurrent partnerships and HIV prevalence disparities by race: linking science and public health practice.

  2009cited by this paper
• Network Analysis in the Social Sciences

  2009cited by this paper
• Birds of a feather, or friend of a friend? using exponential random graph models to investigate adolescent social networks*

  2009cited by this paper
• ergm: A Package to Fit, Simulate and Diagnose Exponential-Family Models for Networks.

  2008influential reference
• Goodness of Fit of Social Network Models

  2008influential reference
• statnet: Software Tools for the Representation, Visualization, Analysis and Simulation of Network Data.

  2008cited by this paper
• An introduction to exponential random graph (p*) models for social networks

  2007cited by this paper
• Model‐based clustering for social networks

  2007cited by this paper
• Advances in exponential random graph (p*) models applied to a large social network

  2007cited by this paper
• Inference in Curved Exponential Family Models for Networks

  2006cited by this paper
• New Specifications for Exponential Random Graph Models

  2006cited by this paper
• Center for Studies in Demography and Ecology Assessing Degeneracy in Statistical Models of Social Networks

  2005cited by this paper
• The collegial phenomenon. The social mechanisms of cooperation among peers in a corporate law partnership

  2003cited by this paper
• The Structure and Function of Complex Networks

  2003cited by this paper
• Markov Chain Monte Carlo Estimation of Exponential Random Graph Models

  2002cited by this paper
• Constrained Monte Carlo Maximum Likelihood for Dependent Data

  1992cited by this paper
• Pseudolikelihood Estimation for Social Networks

  1990cited by this paper
• An Exponential Family of Probability Distributions for Directed Graphs

  1981cited by this paper

• No citing papers are available for this paper.