BFS-based LLM framework reduces causal graph discovery queries from quadratic to linear while incorporating observational data and reporting state-of-the-art results on real graphs.
Causal discovery with language models as imperfect experts, 2023a
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Proposes restricting AI agents to workflow assistance in causal discovery and demonstrates the approach via the causal-learn+ platform on personality data.
citing papers explorer
-
Efficient Causal Graph Discovery Using Large Language Models
BFS-based LLM framework reduces causal graph discovery queries from quadratic to linear while incorporating observational data and reporting state-of-the-art results on real graphs.
-
Causal Discovery in the Era of Agents
Proposes restricting AI agents to workflow assistance in causal discovery and demonstrates the approach via the causal-learn+ platform on personality data.