Towards Robust Offline Evaluation: A Causal and Information Theoretic Framework for Debiasing Ranking Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908302737145856 |
|---|---|
| author | Khatami, Seyedeh Baharan Chakraborty, Sayan Xu, Ruomeng Salimi, Babak |
| author_facet | Khatami, Seyedeh Baharan Chakraborty, Sayan Xu, Ruomeng Salimi, Babak |
| contents | Evaluating retrieval-ranking systems is crucial for developing high-performing models. While online A/B testing is the gold standard, its high cost and risks to user experience require effective offline methods. However, relying on historical interaction data introduces biases-such as selection, exposure, conformity, and position biases-that distort evaluation metrics, driven by the Missing-Not-At-Random (MNAR) nature of user interactions and favoring popular or frequently exposed items over true user preferences.
We propose a novel framework for robust offline evaluation of retrieval-ranking systems, transforming MNAR data into Missing-At-Random (MAR) through reweighting combined with black-box optimization, guided by neural estimation of information-theoretic metrics. Our contributions include (1) a causal formulation for addressing offline evaluation biases, (2) a system-agnostic debiasing framework, and (3) empirical validation of its effectiveness. This framework enables more accurate, fair, and generalizable evaluations, enhancing model assessment before deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03997 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Robust Offline Evaluation: A Causal and Information Theoretic Framework for Debiasing Ranking Systems Khatami, Seyedeh Baharan Chakraborty, Sayan Xu, Ruomeng Salimi, Babak Information Retrieval Evaluating retrieval-ranking systems is crucial for developing high-performing models. While online A/B testing is the gold standard, its high cost and risks to user experience require effective offline methods. However, relying on historical interaction data introduces biases-such as selection, exposure, conformity, and position biases-that distort evaluation metrics, driven by the Missing-Not-At-Random (MNAR) nature of user interactions and favoring popular or frequently exposed items over true user preferences. We propose a novel framework for robust offline evaluation of retrieval-ranking systems, transforming MNAR data into Missing-At-Random (MAR) through reweighting combined with black-box optimization, guided by neural estimation of information-theoretic metrics. Our contributions include (1) a causal formulation for addressing offline evaluation biases, (2) a system-agnostic debiasing framework, and (3) empirical validation of its effectiveness. This framework enables more accurate, fair, and generalizable evaluations, enhancing model assessment before deployment. |
| title | Towards Robust Offline Evaluation: A Causal and Information Theoretic Framework for Debiasing Ranking Systems |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2504.03997 |