Inferring Causal Relations between Two Sequences of Events with Language Models
It is shown in this study that it is possible to leverage the predictive power of Large Language Models (LLMs) to infer causal relations between only two sequences of events, which provides better results than standard causal discovery algorithms on several time series data, even though these data were converted into s...
Nishchal Prasad, Éric Gaussier, Emilie Devijver et al.
· 0 citations