Mitigating Biases in Language Models via Bias Unlearning

• URL: http://arxiv.org/abs/2509.25673v1
• Date: Tue, 30 Sep 2025 02:15:12 GMT
• Title: Mitigating Biases in Language Models via Bias Unlearning
• Authors: Dianqing Liu, Yi Liu, Guoqing Jin, Zhendong Mao,
• Abstract summary: We propose BiasUnlearn, a novel model debiasing framework which achieves targeted debiasing via dual-pathway unlearning mechanisms.<n>The results show that BiasUnlearn outperforms existing methods in mitigating bias in language models while retaining language modeling capabilities.
• Score: 27.565946855618368
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities such as text coherence and task accuracy. And Prompt-based debiasing methods, only effective for predefined trigger words, fail to address deeply embedded stereotypical associations in model parameters. In this paper, we propose BiasUnlearn, a novel model debiasing framework which achieves targeted debiasing via dual-pathway unlearning mechanisms coordinating stereotype forgetting with anti-stereotype retention, while preventing bias polarity reversal through adversarial forget set and dynamic dataset swapping. We conducted extensive experiments with multiple language models across various evaluation benchmarks. The results show that BiasUnlearn outperforms existing methods in mitigating bias in language models while retaining language modeling capabilities. Further experiments reveal that debiasing weights are transferable across model variants, confirming that bias representations become entrenched during pre-training and persist through fine-tuning phases.

Related papers

• BiasEdit: Debiasing Stereotyped Language Models via Model Editing [40.57172805190225]
  We propose BiasEdit, an efficient model editing method to remove stereotypical bias from language models.<n>BiasEdit employs a debiasing loss guiding editor networks to conduct local edits on partial parameters of a language model.<n> Experiments on StereoSet and Crows-Pairs demonstrate the effectiveness, efficiency, and robustness of BiasEdit in eliminating bias.
  arXiv  Detail & Related papers  (2025-03-11T16:25:36Z)
• REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning [18.064064773660174]
  We introduce REFINE-LM, a debiasing method that uses reinforcement learning to handle different types of biases without any fine-tuning. By training a simple model on top of the word probability distribution of a LM, our bias reinforcement learning method enables model debiasing without human annotations. Experiments conducted on a wide range of models, including several LMs, show that our method significantly reduces stereotypical biases while preserving LMs performance.
  arXiv  Detail & Related papers  (2024-08-18T14:08:31Z)
• Projective Methods for Mitigating Gender Bias in Pre-trained Language Models [10.418595661963062]
  Projective methods are fast to implement, use a small number of saved parameters, and make no updates to the existing model parameters. We find that projective methods can be effective at both intrinsic bias and downstream bias mitigation, but that the two outcomes are not necessarily correlated.
  arXiv  Detail & Related papers  (2024-03-27T17:49:31Z)
• 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)
• Learning Debiased Models with Dynamic Gradient Alignment and Bias-conflicting Sample Mining [39.00256193731365]
  Deep neural networks notoriously suffer from dataset biases which are detrimental to model robustness, generalization and fairness. We propose a two-stage debiasing scheme to combat against the intractable unknown biases.
  arXiv  Detail & Related papers  (2021-11-25T14:50:10Z)
• Balancing out Bias: Achieving Fairness Through Training Reweighting [58.201275105195485]
  Bias in natural language processing arises from models learning characteristics of the author such as gender and race. Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables. This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
  arXiv  Detail & Related papers  (2021-09-16T23:40:28Z)
• Learning from others' mistakes: Avoiding dataset biases without modeling them [111.17078939377313]
  State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended task. Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available. We show a method for training models that learn to ignore these problematic correlations.
  arXiv  Detail & Related papers  (2020-12-02T16:10:54Z)
• Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures [62.562760228942054]
  Existing approaches to improve robustness against dataset biases mostly focus on changing the training objective. We propose to augment the input sentences in the training data with their corresponding predicate-argument structures. We show that without targeting a specific bias, our sentence augmentation improves the robustness of transformer models against multiple biases.
  arXiv  Detail & Related papers  (2020-10-23T16:22:05Z)
• 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)
• Towards Robustifying NLI Models Against Lexical Dataset Biases [94.79704960296108]
  This paper explores both data-level and model-level debiasing methods to robustify models against lexical dataset biases. First, we debias the dataset through data augmentation and enhancement, but show that the model bias cannot be fully removed via this method. The second approach employs a bag-of-words sub-model to capture the features that are likely to exploit the bias and prevents the original model from learning these biased features.
  arXiv  Detail & Related papers  (2020-05-10T17:56:10Z)

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.