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.
More from Research
- François Fleuret: perfect inductive bias causes brutal loss drops that gradient descent reads as spikes — francoisfleuret · 2026-11-19
- WebGPU playground lets you experiment with weight-space programming on Qwen3.5-0.8B — wsxiaoys · 2026-11-19
- ViT can express any conv layer mathematically, but CNN priors still win on small edge devices — burny_tech · 2026-11-19
- Eval Cards tracks 309K model-benchmark results; 78% of evals can't be reproduced — davidmanheim · 2026-11-19
- Jason Wei maps which benchmarks frontier labs actually report; four see universal adoption — davidmanheim · 2026-11-19
- PIPETTE fixes RL red-teaming mode collapse to harden LLM agents against prompt injection — Lipeng He · 2026-11-19