#machine learning
May 2025
Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective
It is shown that while observational outcomes can provide valuable supervision, directly fine-tuning models on such data can lead them to learn spurious correlations, and proposes DeconfoundLM, a method that explicitly removes the effect of known confounders from reward signals.
Erfan Loghmani
· arXiv.org · 1 citation