# Rank-LIME: Local Model-Agnostic Feature Attribution for Learning to Rank

arXiv: https://arxiv.org/abs/2212.12722 · HTML: https://mlsanity.com/paper/2212.12722/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 24 Dec 2022.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [S-LIME: Stabilized-LIME for Model Explanation](https://mlsanity.com/paper/2106.07875/) (2021)
- [SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval](https://mlsanity.com/paper/1912.05891/) (2019)
- [NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sorting](https://mlsanity.com/paper/2102.07831/) (2021)
- [Explainable Recommendation via Multi-Task Learning in Opinionated Text Data](https://mlsanity.com/paper/1806.03568/) (2018)
- [A study on the Interpretability of Neural Retrieval Models using DeepSHAP](https://mlsanity.com/paper/1907.06484/) (2019)
- [EXS: Explainable Search Using Local Model Agnostic Interpretability](https://mlsanity.com/paper/1809.03857/) (2018)
- [Explainable Information Retrieval: A Survey](https://mlsanity.com/paper/2211.02405/) (2022)
- [Valid Explanations for Learning to Rank Models](https://mlsanity.com/paper/2004.13972/) (2020)

## Built on by (most cited first, 7 of 7)

- [On the Possibilities of AI-Generated Text Detection](https://mlsanity.com/paper/2304.04736/) (2023)
- [RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank](https://mlsanity.com/paper/2405.01848/) (2024)
- [SurvBeX: An explanation method of the machine learning survival models based on the Beran estimator](https://mlsanity.com/paper/2308.03730/) (2023)
- [ShaRP: Explaining Rankings and Preferences with Shapley Values](https://mlsanity.com/paper/2401.16744/) (2024)
- [Probing Ranking LLMs: A Mechanistic Analysis for Information Retrieval](https://mlsanity.com/paper/2410.18527/) (2024)
- [SurvBeNIM: The Beran-Based Neural Importance Model for Explaining the Survival Models](https://mlsanity.com/paper/2312.06638/) (2023)
- [Explaining Expert Search and Team Formation Systems with ExES](https://mlsanity.com/paper/2405.12881/) (2024)

## Abstract (arXiv)

Understanding why a model makes certain predictions is crucial when adapting it for real world decision making. LIME is a popular model-agnostic feature attribution method for the tasks of classification and regression. However, the task of learning to rank in information retrieval is more complex in comparison with either classification or regression. In this work, we extend LIME to propose Rank-LIME, a model-agnostic, local, post-hoc linear feature attribution method for the task of learning to rank that generates explanations for ranked lists. We employ novel correlation-based perturbations, differentiable ranking loss functions and introduce new metrics to evaluate ranking based additive feature attribution models. We compare Rank-LIME with a variety of competing systems, with models trained on the MS MARCO datasets and observe that Rank-LIME outperforms existing explanation algorithms in terms of Model Fidelity and Explain-NDCG. With this we propose one of the first algorithms to generate additive feature attributions for explaining ranked lists.