No Training Wheels: Steering Vectors for Bias Correction at Inference Time

• URL: http://arxiv.org/abs/2506.18598v1
• Date: Mon, 23 Jun 2025 12:58:54 GMT
• Title: No Training Wheels: Steering Vectors for Bias Correction at Inference Time
• Authors: Aviral Gupta, Armaan Sethi, Ameesh Sethi,
• Abstract summary: We propose a cheap, training-free method inspired by steering vectors used to edit behaviors in large language models.<n>We compute the difference in mean activations between majority and minority groups to define a "bias vector"<n>This leads to reduced classification bias and improved worst-group accuracy.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural network classifiers trained on datasets with uneven group representation often inherit class biases and learn spurious correlations. These models may perform well on average but consistently fail on atypical groups. For example, in hair color classification, datasets may over-represent females with blond hair, reinforcing stereotypes. Although various algorithmic and data-centric methods have been proposed to address such biases, they often require retraining or significant compute. In this work, we propose a cheap, training-free method inspired by steering vectors used to edit behaviors in large language models. We compute the difference in mean activations between majority and minority groups to define a "bias vector," which we subtract from the model's residual stream. This leads to reduced classification bias and improved worst-group accuracy. We explore multiple strategies for extracting and applying these vectors in transformer-like classifiers, showing that steering vectors, traditionally used in generative models, can also be effective in classification. More broadly, we showcase an extremely cheap, inference time, training free method to mitigate bias in classification models.

Related papers

• ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models [26.544938760265136]
  Deep learning models inadvertently learn spurious correlations between targets and non-essential features.<n>In this paper, we propose a novel post hoc spurious bias mitigation framework without requiring group labels.<n>Our framework, termed ShortcutProbe, identifies prediction shortcuts that reflect potential non-robustness in predictions in a given model's latent space.
  arXiv  Detail & Related papers  (2025-05-20T04:21:17Z)
• Improving Bias Mitigation through Bias Experts in Natural Language Understanding [10.363406065066538]
  We propose a new debiasing framework that introduces binary classifiers between the auxiliary model and the main model. Our proposed strategy improves the bias identification ability of the auxiliary model.
  arXiv  Detail & Related papers  (2023-12-06T16:15:00Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• An Exploration of How Training Set Composition Bias in Machine Learning Affects Identifying Rare Objects [0.0]
  It is common to up-weight the examples of the rare class to ensure it isn't ignored. It is also a frequent practice to train on restricted data where the balance of source types is closer to equal. Here we show that these practices can bias the model toward over-assigning sources to the rare class.
  arXiv  Detail & Related papers  (2022-07-07T10:26:55Z)
• Right for the Right Latent Factors: Debiasing Generative Models via Disentanglement [20.41752850243945]
  Key assumption of most statistical machine learning methods is that they have access to independent samples from the distribution of data they encounter at test time. In particular, machine learning models have been shown to exhibit Clever-Hans-like behaviour, meaning that spurious correlations in the training set are inadvertently learnt. We propose to debias generative models by disentangling their internal representations, which is achieved via human feedback.
  arXiv  Detail & Related papers  (2022-02-01T13:16:18Z)
• Fair Group-Shared Representations with Normalizing Flows [68.29997072804537]
  We develop a fair representation learning algorithm which is able to map individuals belonging to different groups in a single group. We show experimentally that our methodology is competitive with other fair representation learning algorithms.
  arXiv  Detail & Related papers  (2022-01-17T10:49:49Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• Prototypical Classifier for Robust Class-Imbalanced Learning [64.96088324684683]
  We propose textitPrototypical, which does not require fitting additional parameters given the embedding network. Prototypical produces balanced and comparable predictions for all classes even though the training set is class-imbalanced. We test our method on CIFAR-10LT, CIFAR-100LT and Webvision datasets, observing that Prototypical obtains substaintial improvements compared with state of the arts.
  arXiv  Detail & Related papers  (2021-10-22T01:55:01Z)
• LOGAN: Local Group Bias Detection by Clustering [86.38331353310114]
  We argue that evaluating bias at the corpus level is not enough for understanding how biases are embedded in a model. We propose LOGAN, a new bias detection technique based on clustering. Experiments on toxicity classification and object classification tasks show that LOGAN identifies bias in a local region.
  arXiv  Detail & Related papers  (2020-10-06T16:42:51Z)
• Understanding Classifier Mistakes with Generative Models [88.20470690631372]
  Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle. In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
  arXiv  Detail & Related papers  (2020-10-05T22:13:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.