Causal Learning Should Embrace the Wisdom of the Crowd

2026-03-03

AI Summary

This work addresses the challenge of learning causal structures—such as directed acyclic graphs (DAGs)—from observational data, a task hindered by combinatorial explosion and observational ambiguity that impede accurate recovery of the global causal graph. To overcome these limitations, the paper proposes a novel human–AI collaborative paradigm that frames causal discovery as a distributed decision-making problem, integrating fragmented knowledge from human experts and large language model (LLM) agents. By leveraging scalable crowdsourcing, interactive knowledge elicitation, expert opinion modeling, robust aggregation algorithms, and LLM-driven simulation, the approach systematically synthesizes diverse insights to effectively reconstruct complete causal structures. This framework transcends the capacity constraints of individual agents, offering a scalable and practical pathway toward more accurate and efficient causal discovery.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Learning causal structures typically represented by directed acyclic graphs (DAGs) from observational data is notoriously challenging due to the combinatorial explosion of possible graphs and inherent ambiguities in observations. This paper argues that causal learning is now ready for the emergence of a new paradigm supported by rapidly advancing technologies, fulfilling the long-standing vision of leveraging human causal knowledge. This paradigm integrates scalable crowdsourcing platforms for data collection, interactive knowledge elicitation for expert opinion modeling, robust aggregation techniques for expert reconciliation, and large language model (LLM)-based simulation for augmenting AI-driven information acquisition. In this paper, we focus on DAG learning for causal discovery and frame the problem as a distributed decision-making task, recognizing that each participant (human expert or LLM agent) possesses fragmented and imperfect knowledge about different subsets of the variables of interest in the causal graph. By proposing a systematic framework to synthesize these insights, we aim to enable the recovery of a global causal structure unachievable by any individual agent alone.We advocate for a new research frontier and outline a comprehensive framework for new research thrusts that range from eliciting, modeling, aggregating, and optimizing human causal knowledge contributions.

Problem

• causal learning
• directed acyclic graph
• crowdsourcing
• expert knowledge
• causal discovery

Innovation

• causal discovery
• crowdsourcing
• large language models
• knowledge aggregation
• directed acyclic graphs