Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recogn…
8kLFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models
Nowadays, Large Language Models (LLMs) have attracted widespread attention due to their powerful performance. However, due to the unavoidable exposure to socially biased data during training, LLMs tend to exhibit social …
Towards Resource Efficient and Interpretable Bias Mitigation in Large Language Models
Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to…
Language ModelingLanguage ModellingThe power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs
This paper studies gender bias in machine translation through the lens of Large Language Models (LLMs). Four widely-used test sets are employed to benchmark various base LLMs, comparing their translation quality and gend…
Machine TranslationNMTTranslationSensing and Steering Stereotypes: Extracting and Applying Gender Representation Vectors in LLMs
Large language models (LLMs) are known to perpetuate stereotypes and exhibit biases. Various strategies have been proposed to mitigate these biases, but most work studies biases in LLMs as a black-box problem without con…