Back to feed
arXiv cs.LG
arXiv cs.LG
5/11/2026
Robustness of Refugee-Matching Gains to Off-Policy Evaluation Choices

Robustness of Refugee-Matching Gains to Off-Policy Evaluation Choices

Short summary

Researchers validate off-policy evaluation methods including inverse probability weighting (IPW) and augmented IPW (AIPW) for assessing refugee-matching interventions in the United States, confirming stable and statistically significant impact estimates across different modeling architectures. Findings align with prior work by Bansak et al. (2018), establishing robust evaluation methodology for this social-policy domain.

  • •IPW and AIPW methods produce consistent impact estimates for refugee matching across variants
  • •Results remain statistically significant across different modeling architectures and assignment procedures
  • •Confirms and extends earlier research on refugee-matching interventions

Generated with AI, which can make mistakes.

Read full article at arXiv cs.LG

Is this a good recommendation for you?

Explore more

Embeddings for Preferences, Not Semantics
arXiv CS.AI
Distributional Reinforcement Learning via the Cram\'er Distance
arXiv cs.LG
TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
arXiv cs.LG
CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment
arXiv CS.AI