Library / Framework · Python
nexttext
nexttext is a lightweight Python toolkit for neutralizing explicit gendered terms in text. Via simple, fast heuristics it helps clean and standardize AI-generated labels, reducing model-induced misgendering and other unwanted linguistic artifacts. It's intended for use in AI pipelines, for both processing training data or filtering model outputs.
What it is
nexttext is a Python library and CLI toolkit for neutralizing text and generating controlled bias to test and improve AI pipelines, offering multiple strategies (lexical, NLP-backed, semantic) for debiasing and injecting bias in text data.
- ai-ethics
- bias
- cross-modal-learning
- data-cleaning
- debias
- fairness
- gender-bias
- heuristics
- knowledge-distillation
- knowledge-transfer
Where it counts
- NLP & LLMs90%
- Machine Learning60%
- Data Science50%
- MLOps30%
- Computer Vision20%
How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.
Around it on the NLP & LLMs board
Whole board- 06Fresta-DiamondLibrary / Framework · Python69.4AdvancedTiago SantosNLP & LLMs
- 07magellanAI Developer Tool · Rust68.8AdvancedLuiz Cesar SpiesNLP & LLMs
- 08nexttextLibrary / Framework · Python66.9AdvancedJarad PeckenpaughNLP & LLMs
- 09gguf-editorAI Developer Tool · Python66.1AdvancedMaster MindNLP & LLMs
- 10TheLuxApp-Ai-ChatBotML Application · TypeScript65.7AdvancedMaster MindNLP & LLMs
