# Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions

arXiv: https://arxiv.org/abs/2605.28780 · HTML: https://mlsanity.com/paper/2605.28780/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Learning De-biased Representations with Biased Representations](https://mlsanity.com/paper/1910.02806/) (2019)
- [CRAFT: Concept Recursive Activation FacTorization for Explainability](https://mlsanity.com/paper/2211.10154/) (2022)
- [MaskTune: Mitigating Spurious Correlations by Forcing to Explore](https://mlsanity.com/paper/2210.00055/) (2022)
- [Discovering and Mitigating Visual Biases through Keyword Explanation](https://mlsanity.com/paper/2301.11104/) (2023)
- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Coarse-to-Fine Concept Bottleneck Models](https://mlsanity.com/paper/2310.02116/) (2023)
- [Discovering environments with XRM](https://mlsanity.com/paper/2309.16748/) (2023)
- [Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence](https://mlsanity.com/paper/2202.03482/) (2022)
- [Group Robust Classification Without Any Group Information](https://mlsanity.com/paper/2310.18555/) (2023)
- [Understanding Video Transformers via Universal Concept Discovery](https://mlsanity.com/paper/2401.10831/) (2024)
- [From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space](https://mlsanity.com/paper/2308.09437/) (2023)
- [SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP](https://mlsanity.com/paper/2408.10202/) (2024)
- [Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?](https://mlsanity.com/paper/2409.13456/) (2024)
- [BendVLM: Test-Time Debiasing of Vision-Language Embeddings](https://mlsanity.com/paper/2411.04420/) (2024)
- [Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods](https://mlsanity.com/paper/2406.12142/) (2024)
- [Consistency and Accuracy of CelebA Attribute Values](https://mlsanity.com/paper/2210.07356/) (2022)
- [Unsupervised Concept Discovery Mitigates Spurious Correlations](https://mlsanity.com/paper/2402.13368/) (2024)
- [Discover and Mitigate Multiple Biased Subgroups in Image Classifiers](https://mlsanity.com/paper/2403.12777/) (2024)
- [Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations](https://mlsanity.com/paper/2407.14974/) (2024)
- [FACE: Faithful Automatic Concept Extraction](https://mlsanity.com/paper/2510.11675/) (2025)
- [ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations](https://mlsanity.com/paper/2403.13870/) (2024)
- [LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiers](https://mlsanity.com/paper/2408.07832/) (2024)

## Abstract (arXiv)

Vision classifiers can exploit spurious correlations, achieving high in-distribution accuracy yet failing under distribution shift. Existing approaches to bias mitigation and analysis often depend on curated datasets, spurious-attribute or group labels, or retraining, which may be infeasible once a model is deployed or the relevant bias is unknown. We present a bias-label-free, post-hoc method for identifying spurious concepts in frozen vision models, relying only on standard class labels from a held-out audit dataset. For each target class, we collect patches from inputs predicted as that class and apply non-negative matrix factorization to intermediate activations to obtain a bank of interpretable concept vectors. Candidate concepts are then ranked with a bias estimator derived from their interaction with backpropagated gradients on misclassified examples: bias concepts tend to get activated when correcting false negatives and suppressed when correcting false positives. On Colored MNIST and Waterbirds the method recovers concepts aligned with the known spurious cue, and on CelebA it surfaces decision-relevant directions that only partially coincide with the annotated gender attribute; suppressing the top-ranked concepts at inference time improves worst-group accuracy by up to 17.9 percentage points on Waterbirds and 10.4 on CelebA without any retraining or parameter updates. Our method identifies decision-relevant spurious directions that need not coincide with annotated ones, providing both an interpretable auditing tool and an actionable debiasing handle for frozen vision models. Code is available at https://github.com/vitryt/label-free-bias-identification.