Beyond Attribute-Centric Fairness: Modeling and Mitigating Unified Bias Representation in Omni-modal Large Language Models

Omni-modal large language models (OLLMs) provide joint multimodal understanding and generation capabilities, making them well-suited to complex environments and promising backbones for next-generation AI. Despite these advances, the harmful stereotypes encoded in such models manifest in increasingly diverse forms, leading to broader and more severe societal consequences. Existing debiasing methods typically impose separate fairness objectives for each sensitive attribute and modality to minimise demographic-dependent variations. However, in omni-modal settings, this attribute-centric paradigm struggles to jointly address diverse social biases with distinct fairness objectives and to generalise beyond predefined attributes. To this end, we propose OmniDebias, one of the first methods for promoting fairness in OLLMs, which employs a bias-centric formulation to extract and mitigate a shared bias representation across attributes and modalities while preserving factual knowledge. Specifically, we exploit activation inconsistencies of a given attribute (e.g., gender) across semantic contexts (e.g., occupations) to disentangle bias from factual knowledge. We further consolidate multiple extracted biases into a shared representation, formulating a unified objective that captures the underlying structure across social biases and generalises to unseen attributes. Extensive experiments demonstrate that eliminating unified bias with both post-hoc editing and fine-tuning can consistently improve fairness across diverse attributes and modalities in OLLMs while maintaining favourable utility.