Causal Discovery with Language Models as Imperfect Experts

Causal Discovery with Language Models as Imperfect Experts

Welcome to the AI research bites. This series of short and informative talks showcases cutting-edge research work from ServiceNow AI Research team. The AI Research Bites are open to all, especially those interested in keeping up with the fast-paced AI research community.

This session features Valentina Zantedeschi's recent work on Causal Discovery with Language Models as Imperfect Experts which explores how expert knowledge can be used to improve the data-driven identification of causal graphs, but where the expert may provide erroneous information. The talk also underlines the essential role of causality in shaping organizational strategies to tackle complex issues such as the underrepresentation of women in STEM.

Paper:
https://arxiv.org/abs/2307.02390

Repo:
https://github.com/StephLong614/Causal-disco

ServiceNow AI Research team:
https://www.servicenow.com/research/