# Counterfactual Evaluation of Ads Ranking Models through Domain Adaptation

arXiv: https://arxiv.org/abs/2409.19824 · HTML: https://mlsanity.com/paper/2409.19824/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 29 Sep 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 6 of 6)

- [The Simpson's Paradox in the Offline Evaluation of Recommendation Systems](https://mlsanity.com/paper/2104.08912/) (2021)
- [Seeker: Real-Time Interactive Search](https://mlsanity.com/paper/1905.13125/) (2019)
- [Causal Transfer Random Forest: Combining Logged Data and Randomized Experiments for Robust Prediction](https://mlsanity.com/paper/2010.08710/) (2020)
- [Adaptive Experimental Design and Counterfactual Inference](https://mlsanity.com/paper/2210.14369/) (2022)
- [Neural Insights for Digital Marketing Content Design](https://mlsanity.com/paper/2302.01416/) (2023)
- [Genie: An Open Box Counterfactual Policy Estimator for Optimizing Sponsored Search Marketplace](https://mlsanity.com/paper/1808.07251/) (2018)

## Abstract (arXiv)

We propose a domain-adapted reward model that works alongside an Offline A/B testing system for evaluating ranking models. This approach effectively measures reward for ranking model changes in large-scale Ads recommender systems, where model-free methods like IPS are not feasible. Our experiments demonstrate that the proposed technique outperforms both the vanilla IPS method and approaches using non-generalized reward models.