LLMs fail causal discovery due to a kernel obstruction in observational learning, but interventional agents using frozen LLMs in Bayesian loops succeed without training on causal graph benchmarks.
Prompting strategies for enabling large language models to infer causation from correlation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
CausalGuard aggregates LLM-proposed and data-pruned DAGs to weight doubly robust pseudo-outcomes and applies conformal calibration to deliver finite-sample marginal coverage for conditional average treatment effects under graph uncertainty.
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
citing papers explorer
-
Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
LLMs fail causal discovery due to a kernel obstruction in observational learning, but interventional agents using frozen LLMs in Bayesian loops succeed without training on causal graph benchmarks.
-
CausalGuard: Conformal Inference under Graph Uncertainty
CausalGuard aggregates LLM-proposed and data-pruned DAGs to weight doubly robust pseudo-outcomes and applies conformal calibration to deliver finite-sample marginal coverage for conditional average treatment effects under graph uncertainty.
-
When Do We Need LLMs? A Diagnostic for Language-Driven Bandits
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.