salesforce/AuditNLG: AuditNLG: Auditing Generative AI Language Modeling for Trustworthiness
github.com · 1,403 words · saved by 1 readers
AuditNLG: Auditing Generative AI Language Modeling for Trustworthiness
Introduction AuditNLG is an open-source library that can help reduce the risks associated with using generative AI systems for language. It provides and aggregates state-of-the-art techniques for detecting and improving trust, making the process simple and easy to ensemble methods. The library supports three aspects of trust detection and improvement: Factualness, Safety, and Constraint. It can be used to determine whether a text fed into or output from a generative AI model has any trust issues, with output alternatives and an explanation provided. Factualness: Determines whether a text…
saved by
related reading
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- CAIS AI Dashboarddashboard.safe.ai
- Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
- Cookbookcookbook.openai.com
- Hume AI - The AI toolkit for voice and emotionhume.ai
- There's An AI For That® — The front page of AItheresanaiforthat.com
- Goodfire AIgoodfire.ai
- Lakera – Test your AI hacking skillsgandalf.lakera.ai
- LangChain: the open agent platform to own your intelligencelangchain.com
- Unrestricted AI API + Enterprise Policy Gateway | abliteration.aiabliteration.ai
- Hugging Face – The AI community building the future.huggingface.co