When Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-Training
This story is from 2026-10-27. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2610.33311v1 Announce Type: new Abstract: How does pre-trained model capacity relate to performance after adaptation for causal tasks? We study two systems built on the Qwen 2.5 family: CausalLLM, which estimates scalar potential outcomes with treatment-specific heads, and CausalGen, which ge…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-27 04:00 · arXiv cs.LG
When Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-Training