Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles

• URL: http://arxiv.org/abs/2606.12088v1
• Date: Wed, 10 Jun 2026 13:49:27 GMT
• Title: Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
• Abstract summary: Most fairness research in NLP assumes direct access to protected attributes such as gender, race, or nationality.<n>This raises a key question: can debiasing succeed without direct access to sensitive attributes?<n>We propose H-SAL, which performs post-hoc concept and attribute erasure using self-description text as an implicit debiasing signal.
• Score: 48.07449275130565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most fairness research in NLP assumes direct access to protected attributes such as gender, race, or nationality. In practice, however, such information is often unavailable due to privacy constraints, missing metadata, or legal restrictions, even though models may infer it from indirect textual cues. This raises a key question: can debiasing succeed without direct access to sensitive attributes? We propose H-SAL, which performs post-hoc concept and attribute erasure using self-description text as an implicit debiasing signal. To support this setting, we introduce a multi-domain Stack Exchange-based fairness benchmark for helpfulness prediction that includes both explicit and implicit signals, enabling comparison between standard debiasing with protected labels and debiasing without access to sensitive information. Across encoder and decoder-only language models, we find that implicit self-description often matches or outperforms explicit-label-based debiasing. Our results broaden representation-level fairness research and provide a new benchmark for studying debiasing under realistic data constraints.

Related papers

• Response Time Enhances Alignment with Heterogeneous Preferences [49.69696266152175]
  We show that augmenting preference datasets with a simple, secondary signal can restore identifiability of the population's average preference.<n>Our results bring promises and open up new opportunities for future data-collection pipelines.
  arXiv  Detail & Related papers  (2026-05-07T22:05:23Z)
• Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization [13.773597081543185]
  We introduce a novel debiasing regularization technique based on the class-wise variance of embeddings. Our method does not require attribute labels and targets any attribute, thus addressing the shortcomings of existing debiasing methods.
  arXiv  Detail & Related papers  (2024-09-29T03:56:50Z)
• SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP [41.62536201065971]
  Large-scale vision-language models, such as CLIP, are known to contain societal bias regarding protected attributes.<n>We introduce a simple-yet-effective debiasing method called SANER that eliminates attribute information from CLIP text features only of attribute-neutral descriptions.
  arXiv  Detail & Related papers  (2024-08-19T17:57:28Z)
• Identifying and Mitigating Social Bias Knowledge in Language Models [52.52955281662332]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.<n>FAST surpasses state-of-the-art baselines with superior debiasing performance.<n>This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• Language-guided Detection and Mitigation of Unknown Dataset Bias [23.299264313976213]
  We propose a framework to identify potential biases as keywords without prior knowledge based on the partial occurrence in the captions. Our framework not only outperforms existing methods without prior knowledge, but also is even comparable with a method that assumes prior knowledge.
  arXiv  Detail & Related papers  (2024-06-05T03:11:33Z)
• Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity [14.564919048514897]
  Existing regulations prohibit model developers from accessing protected attributes. We show that simply querying for fairness metrics can leak the protected attributes of individuals to the model developers. We propose Attribute-Conceal, a novel technique that achieves differential privacy by calibrating noise to the smooth sensitivity of our bias query.
  arXiv  Detail & Related papers  (2022-11-03T20:44:48Z)
• De-biased Representation Learning for Fairness with Unreliable Labels [22.794504690957414]
  We propose a textbfDe-textbfBiased textbfRepresentation Learning for textbfFairness (DBRF) framework. We formulate the de-biased learning framework through information-theoretic concepts such as mutual information and information bottleneck. Experiment results over both synthetic and real-world data demonstrate that DBRF effectively learns de-biased representations towards ideal labels.
  arXiv  Detail & Related papers  (2022-08-01T07:16:40Z)
• When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributes [18.221858247218726]
  We study a novel and practical problem of fair classification in a semi-private setting. Most of the sensitive attributes are private and only a small amount of clean ones are available. We propose a novel framework FairSP that can achieve Fair prediction under the Semi-Private setting.
  arXiv  Detail & Related papers  (2022-07-18T01:10:25Z)
• Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder [92.67156911466397]
  We propose a semi-supervised fair representation learning approach based on adversarial variational autoencoder. We use a bias-aware model to capture inherent bias information on sensitive attribute. We also use a bias-free model to learn debiased fair representations by using adversarial learning to remove bias information from them.
  arXiv  Detail & Related papers  (2022-04-01T15:57:47Z)
• Measuring Fairness of Text Classifiers via Prediction Sensitivity [63.56554964580627]
  ACCUMULATED PREDICTION SENSITIVITY measures fairness in machine learning models based on the model's prediction sensitivity to perturbations in input features. We show that the metric can be theoretically linked with a specific notion of group fairness (statistical parity) and individual fairness.
  arXiv  Detail & Related papers  (2022-03-16T15:00:33Z)
• Fairness via Representation Neutralization [60.90373932844308]
  We propose a new mitigation technique, namely, Representation Neutralization for Fairness (RNF) RNF achieves that fairness by debiasing only the task-specific classification head of DNN models. Experimental results over several benchmark datasets demonstrate our RNF framework to effectively reduce discrimination of DNN models.
  arXiv  Detail & Related papers  (2021-06-23T22:26:29Z)

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.