Demonstration of Generating Explanations for Black-Box Algorithms Using Lewis
Summary: Lewis explains black-box decisions using probabilistic contrastive counterfactuals grounded in user-specified causal models, rather than purely associational feature attribution. It supports global, contextual, and local explanations plus actionable recourse from input-output observations alone. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Paul Y. Wang (University of California San Diego)
- 2. Sainyam Galhotra (University of Chicago)
- 3. Romila Pradhan (University of California San Diego)
- 4. Babak Salimi (University of California San Diego)
BibTeX Citation
@article{wang_vldb21,
title = {{Demonstration of Generating Explanations for Black-Box Algorithms Using Lewis}},
author = {Wang, Paul Y. and Galhotra, Sainyam and Pradhan, Romila and Salimi, Babak},
journal = {PVLDB},
series = {{VLDB} '21},
volume = {14},
number = {12},
pages = {2787--2790},
doi = {10.14778/3476311.3476345},
url = {https://doi.org/10.14778/3476311.3476345},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,000 | Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals | 2021 | SIGMOD | 7.8677069e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,876 | XInsight: eXplainable Data Analysis Through The Lens of Causality | 2023 | SIGMOD |
| 2 | 10,825 | Explaining Black-Box Clustering Pipelines With Cluster-Explorer | 2025 | VLDB |
| 3 | 6,576 | Toward Interpretable and Actionable Data Analysis with Explanations and Causality | 2022 | VLDB |
| 4 | 1,951 | Interpretable Data-Based Explanations for Fairness Debugging | 2022 | SIGMOD |
| 5 | 11,023 | Opening The Black-Box: Explaining Learned Cost Models For Databases | 2025 | VLDB |
| 6 | 5,054 | Explainable AI: Foundations, Applications, Opportunities for Data Management Research | 2022 | SIGMOD |
| 7 | 9,313 | Computing Rule-Based Explanations by Leveraging Counterfactuals | 2023 | VLDB |
| 8 | 7,907 | Provenance-Enabled Explainable AI | 2024 | SIGMOD |
| 9 | 10,709 | CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets | 2025 | SIGMOD |
| 10 | 3,000 | Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals | 2021 | SIGMOD |