English

Soft Measures for Extracting Causal Collective Intelligence

Computation and Language 2025-06-04 v1 Artificial Intelligence Computers and Society Social and Information Networks

Abstract

Understanding and modeling collective intelligence is essential for addressing complex social systems. Directed graphs called fuzzy cognitive maps (FCMs) offer a powerful tool for encoding causal mental models, but extracting high-integrity FCMs from text is challenging. This study presents an approach using large language models (LLMs) to automate FCM extraction. We introduce novel graph-based similarity measures and evaluate them by correlating their outputs with human judgments through the Elo rating system. Results show positive correlations with human evaluations, but even the best-performing measure exhibits limitations in capturing FCM nuances. Fine-tuning LLMs improves performance, but existing measures still fall short. This study highlights the need for soft similarity measures tailored to FCM extraction, advancing collective intelligence modeling with NLP.

Keywords

Cite

@article{arxiv.2409.18911,
  title  = {Soft Measures for Extracting Causal Collective Intelligence},
  author = {Maryam Berijanian and Spencer Dork and Kuldeep Singh and Michael Riley Millikan and Ashlin Riggs and Aadarsh Swaminathan and Sarah L. Gibbs and Scott E. Friedman and Nathan Brugnone},
  journal= {arXiv preprint arXiv:2409.18911},
  year   = {2025}
}

Comments

Camera-ready version accepted for publication in the EMNLP 2024 Workshop NLP4Science

R2 v1 2026-06-28T18:59:46.525Z