Presents a surrogacy framework for LLM-based A/B testing that identifies human average treatment effects through calibration under weaker conditions than full outcome equivalence.
arXiv preprint arXiv:2003.12408 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SLV aggregates expected profit from current inventory through its full selling lifecycle to measure long-term opportunity costs within short A/B test windows.
citing papers explorer
-
Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inference
Presents a surrogacy framework for LLM-based A/B testing that identifies human average treatment effects through calibration under weaker conditions than full outcome equivalence.
-
Measuring Opportunity Cost with Stock Lifetime Value
SLV aggregates expected profit from current inventory through its full selling lifecycle to measure long-term opportunity costs within short A/B test windows.