Preprint
Aug 2026
From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers
LLMs are better viewed as sources of externally validated soft causal priors than as direct evidence of causal structure, according to a systematic evaluation of 12 instruction-tuned open-weight models.
Amit Kumar, Elnur Adl Zarabi, S. Trivedy et al.
· 0 citations