# Towards Two-Stage Counterfactual Learning to Rank

arXiv: https://arxiv.org/abs/2506.20854 · HTML: https://mlsanity.com/paper/2506.20854/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2025.

## Built on by (most cited first, 1 of 1)

- [Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank](https://mlsanity.com/paper/2605.11272/) (2026)

## Abstract (arXiv)

Counterfactual learning to rank (CLTR) aims to learn a ranking policy from user interactions while correcting for the inherent biases in interaction data, such as position bias. Existing CLTR methods assume a single ranking policy that selects top-K ranking from the entire document candidate set. In real-world applications, the candidate document set is on the order of millions, making a single-stage ranking policy impractical. In order to scale to millions of documents, real-world ranking systems are designed in a two-stage fashion, with a candidate generator followed by a ranker. The existing CLTR method for a two-stage offline ranking system only considers the top-1 ranking set-up and only focuses on training the candidate generator, with the ranker fixed. A CLTR method for training both the ranker and candidate generator jointly is missing from the existing literature. In this paper, we propose a two-stage CLTR estimator that considers the interaction between the two stages and estimates the joint value of the two policies offline. In addition, we propose a novel joint optimization method to train the candidate and ranker policies, respectively. To the best of our knowledge, we are the first to propose a CLTR estimator and learning method for two-stage ranking. Experimental results on a semi-synthetic benchmark demonstrate the effectiveness of the proposed joint CLTR method over baselines.