Researcher: specific training and data sampling make models learn spurious associations, preprint next week

anshulkundaje · x · 2026-11-19

Anshul Kundaje notes that models don't naturally learn causality: while carefully controlled training can let models surface causal hypotheses at high success rates, specific training approaches and data sampling strategies can lead models to learn spurious associations — "causality is most certainly not guaranteed." A critical preprint on this is coming next week.

Original post →

More from Research

Research channel →