# Posthoc Interpretability of Learning to Rank Models using Secondary Training Data

arXiv: https://arxiv.org/abs/1806.11330 · HTML: https://mlsanity.com/paper/1806.11330/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2018.

## Built on by (most cited first, 10 of 10)

- [BERTnesia: Investigating the capture and forgetting of knowledge in BERT](https://mlsanity.com/paper/2106.02902/) (2021)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [Reinforced Path Reasoning for Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2207.06674/) (2022)
- [LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation](https://mlsanity.com/paper/2407.02833/) (2024)
- [Learnt Sparsification for Interpretable Graph Neural Networks](https://mlsanity.com/paper/2106.12920/) (2021)
- [ShaRP: Explaining Rankings and Preferences with Shapley Values](https://mlsanity.com/paper/2401.16744/) (2024)
- [Exposing Query Identification for Search Transparency](https://mlsanity.com/paper/2110.07701/) (2021)
- [ExaRanker: Explanation-Augmented Neural Ranker](https://mlsanity.com/paper/2301.10521/) (2023)
- [SparCAssist: A Model Risk Assessment Assistant Based on Sparse Generated Counterfactuals](https://mlsanity.com/paper/2205.01588/) (2022)
- [Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals](https://mlsanity.com/paper/2608.21662/) (2026)

## Abstract (arXiv)

Predictive models are omnipresent in automated and assisted decision making scenarios. But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features influence the model prediction avoiding algorithmic transparency. Rankings are ordering over items encoding implicit comparisons typically learned using a family of features using learning-to-rank models. In this paper we focus on how best we can understand the decisions made by a ranker in a post-hoc model agnostic manner. We operate on the notion of interpretability based on explainability of rankings over an interpretable feature space. Furthermore we train a tree based model (inherently interpretable) using labels from the ranker, called secondary training data to provide explanations. Consequently, we attempt to study how well does a subset of features, potentially interpretable, explain the full model under different training sizes and algorithms. We do experiments on the learning to rank datasets with 30k queries and report results that serve show in certain settings we can learn a faithful interpretable ranker.