LIRME: Locally Interpretable Ranking Model Explanation
The DOI matches its Crossref record; 12 of the 14 references it cites were found in a registry or an index.
Abstract
Information retrieval (IR) models often employ complex variations in term weights to compute an aggregated similarity score of a query-document pair. Treating IR models as black-boxes makes it difficult to understand or explain why certain documents are retrieved at top-ranks for a given query. Local explanation models have emerged as a popular means to understand individual predictions of classification models. However, there is no systematic investigation that learns to interpret IR models, which is in fact the core contribution of our work in this paper. We explore three sampling methods to train an explanation model and propose two metrics to evaluate explanations generated for an IR model. Our experiments reveal some interesting observations, namely that a) diversity in samples is important for training local explanation models, and b) the stability of a model is inversely proportional to the number of parameters used to explain the model.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Examples include rank order correlation [27,78,230,257], top-k intersection [78], cosine similarity [52], rule match [136], normalized distance [8], and the structural similarity index (SSIM) [60].”
From From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2023) · cites this paper as [257]
Citations
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 1×
“A wide range of modelagnostic local explanation approaches have been proposed for ML tasks [5, 8], most of them focusing on providing an instance-wise explanation of the output of the model as either a subset of input”
BackgroundMethods for interpreting and understanding deep neural networks
Montavon, G., Samek, W., & Müller, K.-R. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2017.10.011 · Cited by 2,665 · cited 1×
“A wide range of model-agnostic local explanation approaches have been proposed for ML tasks [5, 8], most of them focusing on providing an instance-wise explanation of the output of the model as either a subset of input Permission to make digital or hard copies of all or part of this work for…”
BackgroundAnchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · cited 1×
“ACM ISBN 978-1-4503-6172-9/19/07... $15.00 https://doi.org/10.1145/nnnnnnn.nnnnnnn features [3, 10], or a weighted distribution of feature importance [6, 9].”
BackgroundInfluentialMeasuring and Mitigating Unintended Bias in Text Classification
Dixon, L., Li, J., Sorensen, J., Thain, N., & Vasserman, L. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278729 · Cited by 674 · cited 1×
“It has been shown that complex machine learning (ML) models can encode different biases [4] and may present myopic results [2] to users, leading researchers to investigate ways of ‘explaining’ model outcomes.”
BackgroundLinear feature-based models for information retrieval
Metzler, D., & Bruce Croft, W. (2007) · Information Retrieval · doi:10.1007/s10791-006-9019-z · Cited by 372 · cited 1×
“A ranking function can be represented as S ( D , Q ) = (cid:205) t ∈ D ∩ Q w ( t , D ) , where w ( t , D ) represents the term weight of term t in a document D [7].”
BackgroundForgetting personal data and revoking consent under the GDPR: Challenges and proposed solutions
Politou, E., Alepis, E., & Patsakis, C. (2018) · Journal of Cybersecurity · doi:10.1093/cybsec/tyy001 · Cited by 313 · cited 1×
“Providing explanations can also be now required by law, mandated by regulations such as GDPR [1], wherein commercial ranking services may now be required to ‘explain’ its consumers why a document is retrieved for a query.”
BackgroundEXS: Explainable Search Using Local Model Agnostic Interpretability
Singh, J., & Anand, A. (2019) · Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining · doi:10.1145/3289600.3290620 · Cited by 114
Research works printed but not linked: 4
- T. Bolukbasi, K. Chang, J. Y. Zou, V. Saligrama, and A. Kalai. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. CoRR, abs/1607.06520, 2016. · arXiv
- J. Chen, L. Song, M. J. Wainwright, and M. I. Jordan. Learning to explain: An information-theoretic perspective on model interpretation. arXiv preprint arXiv:1802.07814, 2018. · arXiv
- Z. C. Lipton. The mythos of model interpretability. arXiv:1606.03490, 2016. · arXiv
- 10.5555/3295222.3295230 · doi:10.5555/3295222.3295230
Cited by
Nauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · ACM Computing Surveys · doi:10.1145/3583558 · Cited by 590
Explainable Information Retrieval: A SurveyPreprint
Anand, A., Lyu, L., Idahl, M., Wang, Y., Wallat, J., & Zhang, Z. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.02405 · Cited by 105
“Similarly, Verma and Ganguly [125] adapt LIME to create locally interpretable ranking model explanations (LIRME).”
BackgroundInfluentialExplainable Information Retrieval
Anand, A., Sen, P., Saha, S., Verma, M., & Mitra, M. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3594249 · Cited by 51
Self-citationA Systematic Review of Fairness, Accountability, Transparency, and Ethics in Information Retrieval
Bernard, N., & Balog, K. (2023) · ACM Computing Surveys · doi:10.1145/3637211 · Cited by 67
Interpretable Ranking with Generalized Additive Models
Zhuang, H., Wang, X., Bendersky, M., Grushetsky, A., Wu, Y., Mitrichev, P., Sterling, E., Bell, N., Ravina, W., & Qian, H. (2021) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3437963.3441796 · Cited by 59
“In the specific application of learning-to-rank, there are a few recent studies [49, 55, 56, 58] focusing on generating post-hoc explanations for existing models.”
Background
Metadata
- Authors
- Verma, M., & Ganguly, D.
- Affiliations
- Verizon (United States) (US)
- IBM (Ireland) (IE)
- Venue
- Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Published
- 2019-07-18
- Pages
- 1281-1284
- OpenAlex
- W2955573083
- Cited by
- 64
- References
- 14
- Citations by year
- 2026: 4 · 2025: 10 · 2024: 10 · 2023: 12 · 2022: 11 · 2021: 7 · 2020: 9 · 2019: 1
- FWCI
- 2.68
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- term weighting, query-document similarity, sampling methods, model stability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: LIRME: Locally Interpretable Ranking Model Explanation. https://app.cochat.ai/papers/10.1145/3331184.3331377
- The paper
- Verma, M., & Ganguly, D. (2019). LIRME: Locally Interpretable Ranking Model Explanation. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. https://doi.org/10.1145/3331184.3331377
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.