Evaluating Causal Reasoning in LLMs: A Case Study in the Challenges of Procedural Generation
This paper examines what can be reliably inferred when LLMs perform well on test sets produced by CLadder and finds that even simple models such as random forests perform well on CLadder-generated data sets after training on a sample of generated data.
Justin Clarke, Isha Karn, Patrick Murray et al.
· 0 citations