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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LMT is a Bayesian method that fuses LLM-derived textual priors with temporal Poisson likelihoods to discover causal graphs from alarm event records.
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.
-
LMT: A Bayesian Framework for Causal Discovery from Textual Alarm Records in Manufacturing Systems
LMT is a Bayesian method that fuses LLM-derived textual priors with temporal Poisson likelihoods to discover causal graphs from alarm event records.