Methods › Reinforcement Learning › Exploration Strategies › Counterfactuals

Counterfactuals Explanations

Counterfactuals

400 papers tagged archive 2025-07-28

Introduced by Sandra Wachter et al. in Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

The archive carries no description for this method.

PaperSource

Papers archive 2025-07-28

30 shown of 400, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 219 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
counterfactual304
Decision Making35
Fairness35
Counterfactual Explanation34
Causal Inference26
Explainable Artificial Intelligence (XAI)25
Data Augmentation24
Attribute23
Explainable artificial intelligence21
Counterfactual Reasoning20
valid19
Diversity17
Sentiment Analysis12
Time Series12
Counterfactual Inference11
Language Modelling11
model11
Reinforcement Learning (RL)9
Sentence9
BIG-bench Machine Learning8

Usage over time archive 2025-07-28

Papers per year tagged with Counterfactuals: 2017 to 2025, peak 89 89 0 2017: 1 paper 2017 2018: 4 papers 2018 2019: 16 papers 2019 2020: 37 papers 2020 2021: 62 papers 2021 2022: 65 papers 2022 2023: 89 papers 2023 2024: 82 papers 2024 2025: 44 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (400 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Exploration Strategies

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections