mlsanityData to 14 Oct 2026

Guided Data Generation for Understanding Model Behavior

arXiv 2502.06658 ↗First posted 10 Feb 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a method for generating distributions over the input space as an inspection tool for understanding trained models. Our framework poses questions of the form ``which inputs would make a trained model exhibit a specified behavior?'' and encodes each question through a guidance function. The generated data provide insights into how the models behave. To showcase our framework, we pose queries such as generating distributions of data where a specified label would be predicted by the model, where two distinct models would disagree, where the output is sensitive to parameter perturbations, and where predictions would be risky. Our method can be applied with a variety of classification and regression tasks and on a range of model types.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

21 of 32 references.

References · 21

  1. 2022Generative Adversarial Networkscited by 5,627
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  5. 2017Counterfactual Fairnesscited by 804
  6. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  7. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  8. 2019Predictive Multiplicity in Classificationcited by 166
  9. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  10. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  11. 2019Rank-normalization, folding, and localization: An improved widehatR for assessing convergence of MCMCcited by 93
  12. 2016Understanding data augmentation for classification: when to warp?cited by 74
9 more
  1. 2020Generalized Energy Based Modelscited by 73
  2. 2018Data augmentation using synthetic data for time series classification with deep residual networkscited by 38
  3. 2020Gibbs Sampling with Peoplecited by 28
  4. 2024TabPFGen -- Tabular Data Generation with TabPFNcited by 28
  5. 2023GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanationscited by 27
  6. 2024Eliciting the Priors of Large Language Models using Iterated In-Context Learningcited by 19
  7. 2024TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Modelscited by 16
  8. 2021An Introduction to Variational Inferencecited by 12
  9. 2024InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretationcited by 10

Built on by

Not cited yet.