# CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs

arXiv: https://arxiv.org/abs/2505.11060 · HTML: https://mlsanity.com/paper/2505.11060/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [Domino: Discovering Systematic Errors with Cross-Modal Embeddings](https://mlsanity.com/paper/2203.14960/) (2022)
- [Concept-based Explainable Artificial Intelligence: A Survey](https://mlsanity.com/paper/2312.12936/) (2023)
- [Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations](https://mlsanity.com/paper/2011.12854/) (2020)
- [Distilling Model Failures as Directions in Latent Space](https://mlsanity.com/paper/2206.14754/) (2022)
- [Fairwashing Explanations with Off-Manifold Detergent](https://mlsanity.com/paper/2007.09969/) (2020)
- [Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation](https://mlsanity.com/paper/2305.02231/) (2023)
- [Discovering and Mitigating Visual Biases through Keyword Explanation](https://mlsanity.com/paper/2301.11104/) (2023)
- [Diagnosing and Rectifying Vision Models using Language](https://mlsanity.com/paper/2302.04269/) (2023)
- [Describing like humans: on diversity in image captioning](https://mlsanity.com/paper/1903.12020/) (2019)
- [Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning](https://mlsanity.com/paper/2208.08831/) (2022)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [PRIME: Prioritizing Interpretability in Failure Mode Extraction](https://mlsanity.com/paper/2310.00164/) (2023)

## Built on by (most cited first, 1 of 1)

- [Low-cost concept-based localized explanations: How far can we get with training-free approaches?](https://mlsanity.com/paper/2606.29069/) (2026)

## Abstract (arXiv)

Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level features like heatmaps. A major challenge for these concept-based methods is the lack of image annotations indicating potentially bias-inducing concepts, since creating such annotations requires detailed labeling for each dataset and concept, which is highly labor-intensive. We present CUBIC (Concept embeddings for Unsupervised Bias IdentifiCation), a novel method that automatically discovers interpretable concepts that may bias classifier behavior. Unlike existing approaches, CUBIC does not rely on predefined bias candidates or examples of model failures tied to specific biases, as such information is not always available. Instead, it leverages image-text latent space and linear classifier probes to examine how the latent representation of a superclass labelunicodex2014shared by all instances in the datasetunicodex2014is influenced by the presence of a given concept. By measuring these shifts against the normal vector to the classifier's decision boundary, CUBIC identifies concepts that significantly influence model predictions. Our experiments demonstrate that CUBIC effectively uncovers previously unknown biases using Vision-Language Models (VLMs) without requiring the samples in the dataset where the classifier underperforms or prior knowledge of potential biases.