Fine-tuning LLMs with Cross-Attention-based Weight Decay for Bias Mitigation

ACL ARR 2025 February Submission908 Authors

Abstract: Large Language Models (LLMs) excel in Natural Language Processing (NLP) tasks but often propagate societal biases from their training data, leading to discriminatory outputs. These biases are amplified by the models' self-attention mechanisms, which disproportionately emphasize biased correlations with sensitive tokens, like "he" or "she", reflecting the sensitive attributes such as gender and race. To address this issue, we propose a novel fine-tuning method, called Cross-Attention-based Weight Decay (CrAWD), which modifies the LLM architecture to mitigate bias. CrAWD introduces a cross-attention mechanism between an input sequence and a sensitive token sequence, enabling the model to identify and selectively decay the attention weights of tokens associated with sensitive tokens. This reduces the influence of biased association on the model's generation while maintaining task performance. Evaluations on real-world datasets demonstrate the effectiveness of our proposed CrAWD method. Notably, our method can handle multiple sensitive attributes by adjusting the sensitive token sequence, and it does not require full knowledge of sensitive tokens presented in the dataset, underscoring CrAWD's versatility in promoting fair LLMs across various applications.

Paper Type: Long

Research Area: Ethics, Bias, and Fairness

Research Area Keywords: model bias/unfairness mitigation, fine-tuning

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 908