DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning

Title:DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning

Abstract:Large Language Models (LLMs) exhibit strong natural language understanding capabilities but also inherit and amplify societal biases, particularly gender bias, raising fairness concerns. Existing prompt-based debiasing strategies share a key limitation: they fail to disentangle gender information from task semantics. Bias steering compels models to overemphasize gender cues, while reasoning-based prompting induces gender-biased reasoning chains. To address these challenges, we propose this http URL (Decoupled Reasoning for Gender-Aware Prompting), an automated and model-agnostic pipeline that mitigates gender bias while preserving model performance. this http URL generates gender-neutral reasoning traces and applies them as in-context demonstrations during inference, effectively decoupling gender attributes from task semantics without modifying model parameters. Extensive experiments on coreference resolution and question-answering tasks across six LLMs demonstrate this http URL's effectiveness, generalizability, and robustness, supported by detailed mechanism analyses. Moreover, this http URL can be extended to vision-language models (VLMs), achieving substantial bias reduction.

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

arXiv:2502.11603 [cs.CL]

(or arXiv:2502.11603v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2502.11603 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.