# Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing

arXiv: https://arxiv.org/abs/2501.14457 · HTML: https://mlsanity.com/paper/2501.14457/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 59 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla](https://mlsanity.com/paper/2307.09458/) (2023)
- [How well do Large Language Models perform in Arithmetic tasks?](https://mlsanity.com/paper/2304.02015/) (2023)
- [Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue](https://mlsanity.com/paper/2401.04700/) (2024)
- [Sustainable Modular Debiasing of Language Models](https://mlsanity.com/paper/2109.03646/) (2021)
- [Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics](https://mlsanity.com/paper/2410.21272/) (2024)

## Built on by (most cited first, 14 of 14)

- [Understanding How Value Neurons Shape the Generation of Specified Values in LLMs](https://mlsanity.com/paper/2505.17712/) (2025)
- [Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare](https://mlsanity.com/paper/2502.13319/) (2025)
- [Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models](https://mlsanity.com/paper/2508.02360/) (2025)
- [Large Language Models Develop Novel Social Biases Through Adaptive Exploration](https://mlsanity.com/paper/2511.06148/) (2025)
- [Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation](https://mlsanity.com/paper/2605.03058/) (2026)
- [Locating and Controlling Implicit Personalization in Large Language Models](https://mlsanity.com/paper/2608.11735/) (2026)
- [The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection](https://mlsanity.com/paper/2509.15896/) (2025)
- [Aligned but Stereotypical? How System Prompts Shape Demographic Bias in LLM-Based Text-to-Image Models](https://mlsanity.com/paper/2512.04981/) (2025)
- [Tracing Stereotypes in Pre-trained Transformers: From Biased Neurons to Fairer Models](https://mlsanity.com/paper/2601.05663/) (2026)
- [Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues](https://mlsanity.com/paper/2601.12868/) (2026)
- [Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement](https://mlsanity.com/paper/2601.21864/) (2026)
- [GKnow: Measuring the Entanglement of Gender Bias and Factual Gender](https://mlsanity.com/paper/2605.12299/) (2026)
- [Demographic Prompting at Scale: When More Attributes Hurt LLM--Human Agreement](https://mlsanity.com/paper/2607.10590/) (2026)
- [Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding](https://mlsanity.com/paper/2608.07353/) (2026)

## Abstract (arXiv)

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.