Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing

• URL: http://arxiv.org/abs/2501.14457v1
• Date: Fri, 24 Jan 2025 12:41:30 GMT
• Title: Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing
• Abstract summary: Large language models (LLMs) often exhibit gender bias, posing challenges for their safe deployment.<n>Our analysis reveals pervasive bias across models and identifies specific neuron circuits, including gender neurons and general neurons.<n>We propose an interpretable neuron editing method that combines logit-based and causal-based strategies to selectively target biased neurons.
• Score: 19.472889262384818
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) often exhibit gender bias, posing challenges for their safe deployment. Existing methods to mitigate bias lack a comprehensive understanding of its mechanisms or compromise the model's core capabilities. To address these issues, we propose the CommonWords dataset, to systematically evaluate gender bias in LLMs. Our analysis reveals pervasive bias across models and identifies specific neuron circuits, including gender neurons and general neurons, responsible for this behavior. Notably, editing even a small number of general neurons can disrupt the model's overall capabilities due to hierarchical neuron interactions. Based on these insights, we propose an interpretable neuron editing method that combines logit-based and causal-based strategies to selectively target biased neurons. Experiments on five LLMs demonstrate that our method effectively reduces gender bias while preserving the model's original capabilities, outperforming existing fine-tuning and editing approaches. Our findings contribute a novel dataset, a detailed analysis of bias mechanisms, and a practical solution for mitigating gender bias in LLMs.

Related papers

• Interpretable Debiasing of Vision-Language Models for Social Fairness [55.85977929985967]
  We introduce an interpretable, model-agnostic bias mitigation framework, DeBiasLens, that localizes social attribute neurons in Vision-Language models.<n>We train SAEs on facial image or caption datasets without corresponding social attribute labels to uncover neurons highly responsive to specific demographics.<n>Our research lays the groundwork for future auditing tools, prioritizing social fairness in emerging real-world AI systems.
  arXiv  Detail & Related papers  (2026-02-27T13:37:11Z)
• KnowBias: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement [5.243877326529689]
  Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment.<n>We propose KnowBias, a framework that mitigates bias by strengthening, rather than suppressing, neurons encoding bias-knowledge.<n>KnowBias identifies neurons encoding bias knowledge using a small set of bias-knowledge questions via attribution-based analysis, and selectively enhances them at inference time.
  arXiv  Detail & Related papers  (2026-01-29T15:32:38Z)
• Cognitive Debiasing Large Language Models for Decision-Making [71.2409973056137]
  Large language models (LLMs) have shown potential in supporting decision-making applications. We propose a cognitive debiasing approach, called self-debiasing, that enhances the reliability of LLMs. Our method follows three sequential steps -- bias determination, bias analysis, and cognitive debiasing -- to iteratively mitigate potential cognitive biases in prompts.
  arXiv  Detail & Related papers  (2025-04-05T11:23:05Z)
• The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models [78.69526166193236]
  Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases. We propose sc Social Bias Neurons to accurately pinpoint units (i.e., neurons) in a language model that can be attributed to undesirable behavior, such as social bias. As measured by prior metrics from StereoSet, our model achieves a higher degree of fairness while maintaining language modeling ability with low cost.
  arXiv  Detail & Related papers  (2024-06-14T15:41:06Z)
• Locating and Mitigating Gender Bias in Large Language Models [40.78150878350479]
  Large language models (LLM) are pre-trained on extensive corpora to learn facts and human cognition which contain human preferences. This process can inadvertently lead to these models acquiring biases and prevalent stereotypes in society. We propose the LSDM (Least Square Debias Method), a knowledge-editing based method for mitigating gender bias in occupational pronouns.
  arXiv  Detail & Related papers  (2024-03-21T13:57:43Z)
• Cognitive Bias in Decision-Making with LLMs [19.87475562475802]
  Large language models (LLMs) offer significant potential as tools to support an expanding range of decision-making tasks. LLMs have been shown to inherit societal biases against protected groups, as well as be subject to bias functionally resembling cognitive bias. Our work introduces BiasBuster, a framework designed to uncover, evaluate, and mitigate cognitive bias in LLMs.
  arXiv  Detail & Related papers  (2024-02-25T02:35:56Z)
• Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes [73.12947922129261]
  We leverage the zero-shot capabilities of large language models to reduce stereotyping. We show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups. We hope this work opens inquiry into other zero-shot techniques for bias mitigation.
  arXiv  Detail & Related papers  (2024-02-03T01:40:11Z)
• Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination [54.865941973768905]
  We propose a novel and practical bias mitigation method, CRISPR, to eliminate bias neurons of language models in instruction-following settings. CRISPR automatically determines biased outputs and categorizes neurons that affect the biased outputs as bias neurons using an explainability method. Experimental results demonstrate the effectiveness of our method in mitigating biases under zero-shot instruction-following settings without losing the model's task performance and existing knowledge.
  arXiv  Detail & Related papers  (2023-11-16T07:16:55Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving [3.114945725130788]
  We propose a novel methodology that leverages a causal inference framework to effectively remove gender bias. Our comprehensive experiments show that the proposed method achieves state-of-the-art results in gender-debiasing tasks.
  arXiv  Detail & Related papers  (2021-12-09T19:57:22Z)
• Balancing Biases and Preserving Privacy on Balanced Faces in the Wild [50.915684171879036]
  There are demographic biases present in current facial recognition (FR) models. We introduce our Balanced Faces in the Wild dataset to measure these biases across different ethnic and gender subgroups. We find that relying on a single score threshold to differentiate between genuine and imposters sample pairs leads to suboptimal results. We propose a novel domain adaptation learning scheme that uses facial features extracted from state-of-the-art neural networks.
  arXiv  Detail & Related papers  (2021-03-16T15:05:49Z)
• Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias [45.956112337250275]
  We propose a methodology grounded in the theory of causal mediation analysis for interpreting which parts of a model are causally implicated in its behavior. We apply this methodology to analyze gender bias in pre-trained Transformer language models. Our mediation analysis reveals that gender bias effects are (i) sparse, concentrated in a small part of the network; (ii) synergistic, amplified or repressed by different components; and (iii) decomposable into effects flowing directly from the input and indirectly through the mediators.
  arXiv  Detail & Related papers  (2020-04-26T01:53:03Z)

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.