IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data
This addresses the challenge of expensive data collection and unrealistic assumptions in causal discovery for researchers, though it appears incremental as it builds on existing statistical and LLM-based methods.
The paper tackles the problem of causal discovery without pre-existing tabular data by introducing IRIS, a framework that automatically collects documents, extracts variables, and uncovers causal relations, achieving real-time discovery from initial variables alone.
Causal discovery is fundamental to scientific research, yet traditional statistical algorithms face significant challenges, including expensive data collection, redundant computation for known relations, and unrealistic assumptions. While recent LLM-based methods excel at identifying commonly known causal relations, they fail to uncover novel relations. We introduce IRIS (Iterative Retrieval and Integrated System for Real-Time Causal Discovery), a novel framework that addresses these limitations. Starting with a set of initial variables, IRIS automatically collects relevant documents, extracts variables, and uncovers causal relations. Our hybrid causal discovery method combines statistical algorithms and LLM-based methods to discover known and novel causal relations. In addition to causal discovery on initial variables, the missing variable proposal component of IRIS identifies and incorporates missing variables to expand the causal graphs. Our approach enables real-time causal discovery from only a set of initial variables without requiring pre-existing datasets.