UnBias-Plus: Detect, Explain, and Rewrite Bias
This toolkit addresses the need for comprehensive bias analysis tools for researchers and practitioners in NLP, but it is an incremental contribution combining existing capabilities.
UnBias-Plus is an open-source toolkit that detects, explains, and rewrites bias in text, providing segment-level classification, span localization, neutral rewriting, and reasoning. It is available through multiple interfaces and publicly released.
Bias in natural language remains a persistent challenge in both human-written and AI-generated content, affecting domains such as journalism, education, and AI research. Most existing detection methods identify only the presence of bias, with limited support for granular detection, interpretable explanations, neutral rewriting, and openly available trained models. We present UnBias-Plus, an open-source toolkit unifying (1) segment-level multi-class bias classification, (2) biased span localization, (3) neutral text rewriting, and (4) reasoning for each decision. Available via Python, CLI, REST API, and web interfaces, UnBias-Plus supports accessible bias analysis. The toolkit, source code, models, datasets, and documentation are publicly available.