一站式检测解释并重写文本偏见，支持多粒度分析与可解释重写。
UnBias-Plus: Detect, Explain, and Rewrite Bias
- 统一四功能：分段分类、定位偏见片段、中性重写、决策推理。
- 支持细粒度偏见识别与可解释的中性文本重构。
- 开源可用，提供多种接口，适合内容审核与AI伦理研究者。
自然语言中的偏见在人工撰写和AI生成内容中持续存在，影响新闻、教育及AI研究等领域。现有检测方法大多仅能识别偏见存在，缺乏对偏见的细粒度检测、可解释性说明、中性重写能力，以及公开可用的训练模型。我们提出UnBias-Plus，一个开源工具包，集成（1）分段级多类别偏见分类，（2）偏见片段定位，（3）中性文本重写，以及（4）每项决策的推理过程。该工具通过Python、CLI、REST API和网页界面提供支持，实现便捷的偏见分析。工具包、源代码、模型、数据集及文档均公开可用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。