mlsanityData to 14 Oct 2026

GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language

arXiv 2206.15007 ↗First posted 30 Jun 2022cs.CL cs.CV cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Helping end users comprehend the abstract distribution shifts can greatly facilitate AI deployment. Motivated by this, we propose a novel task, dataset explanation. Given two image data sets, dataset explanation aims to automatically point out their dataset-level distribution shifts with natural language. Current techniques for monitoring distribution shifts provide inadequate information to understand datasets with the goal of improving data quality. Therefore, we introduce GSCLIP, a training-free framework to solve the dataset explanation task. In GSCLIP, we propose the selector as the first quantitative evaluation method to identify explanations that are proper to summarize dataset shifts. Furthermore, we leverage this selector to demonstrate the superiority of a generator based on language model generation. Systematic evaluation on natural data shift verifies that GSCLIP, a combined system of a hybrid generator group and an efficient selector is not only easy-to-use but also powerful for dataset explanation at scale.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 30 Jun 2022.

Builds on

16 of 32 references.

References · 16

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  6. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  7. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  8. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  9. 2020In Search of Lost Domain Generalizationcited by 1,054
  10. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  11. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 295
  12. 2018Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shiftcited by 243
4 more
  1. 2022Domino: Discovering Systematic Errors with Cross-Modal Embeddingscited by 156
  2. 2019Imbalance Problems in Object Detection: A Reviewcited by 118
  3. 2022MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflictscited by 81
  4. 2021MLDemon: Deployment Monitoring for Machine Learning Systemscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 4; 2026: 3.

14 papers.

Sort:

By area:

  1. 2024Rethinking Interpretability in the Era of Large Language Modelscited by 111
  2. 2023Goal Driven Discovery of Distributional Differences via Language Descriptionscited by 62
  3. 2023Explaining black box text modules in natural language with language modelscited by 62
  4. 2023Goal-Driven Explainable Clustering via Language Descriptionscited by 58
  5. 2023Describing Differences in Image Sets with Natural Languagecited by 53
  6. 2024Discover and Mitigate Multiple Biased Subgroups in Image Classifierscited by 11
  7. 2025Causal Inference on Outcomes Learned from Textcited by 8
  8. 2024"What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shiftscited by 5
  9. 2025Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Imagescited by 1
  10. 2025Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Modelscited by 1
  11. 2026Agentic-imodels: Evolving agentic interpretability tools via autoresearchcited by 1
  12. 2025Multi Attribute Bias Mitigation via Representation Learningcited by 0
2 more
  1. 2026LatentDiff: Scaling Semantic Dataset Comparison to Millions of Imagescited by 0
  2. 2026Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Languagecited by 0