ai-transparency

Star

Here are 11 public repositories matching this topic...

Language:All

Filter by language

All11 Python3 Jupyter Notebook2 TypeScript2 HTML1

Sort:Most stars

Sort options

Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

aichatwatch /aicw

Star14

AI Chat Watch (AICW) - free open-source tool for GEO marketers that track what & how AI mentions brands, products, companies.

marketing observability competitive-intelligence ai-agents claude martech brand-monitoring ai-observability chatgpt llm-evaluation llm-monitoring ai-transparency

UpdatedOct 30, 2025
TypeScript

EyKettle /IIIA

Star5

Indice d'implication de l'intelligence artificielle

rules framework ai attribution standardization digital-media grading-system video-production ai-ethics content-creation media-studies creator-economy classification-system human-ai-collaboration creative-industry ai-transparency ai-involvement-index

UpdatedJun 17, 2025

The LLM Unlearning repository is an open-source project dedicated to the concept of unlearning in Large Language Models (LLMs). It aims to address concerns about data privacy and ethical AI by exploring and implementing unlearning techniques that allow models to forget unwanted or sensitive data. This ensures that AI models comply with privacy.

privacy-preserving-machine-learning ai-privacy trustworthy-ai llm-unlearning exact-unlearning ai-transparency efficient-unlearning approximate-unlearning unlearning-framework data-unlearning data-forgetting

UpdatedDec 16, 2025
Python

aygong /ClipMind

Star4

Code for the paper "ClipMind: A Framework for Auditing Short-Format Video Recommendations Using Multimodal AI Models"

machine-learning embedding-models social-graph social-computing computational-social-science multimodal-deep-learning recommendation-systems algorithmic-auditing social-media-platforms ai-transparency short-format-video auditing-framework

UpdatedJun 26, 2025
Jupyter Notebook

ShaliniAnandaPhD /PRISM

Sponsor

Star2

pRISM is a repository that combines Retrieval-Augmented Generation (RAG) with a multi-LLM voting approach to create accurate and reliable AI-generated outputs. It integrates multiple language models, including Mistral, Claude 3.5, and OpenAI, to enhance performance through advanced consensus techniques

multi-model lora fine-tuning weighted-majority legal-ai document-processing-pipeline llm phi-4 semantic-ai ai-transparency

UpdatedJun 20, 2025
Python

aaronjl86 /Clarity_Framework

Star1

A simple, universal system that labels ai responses so anyone can instantly tell what the output is and how it’s meant to be used.

intent-classification classification-framework universal-tagset ai-content-detector ai-generated-content ai-transparency ai-generated-media ai-tagging metadata-tagging intent-driven-development

UpdatedNov 15, 2025

Del1r1ous /Antagonistic-Cooperation-and-Pragmatic-Existentialism

Star1

Pragmatic Existentialism & Antagonistic Cooperation: A formal theory positing that truth and ethics emerge from the need for coherent systems to overcome shared obstacles, defining belief utility by survival fitness and cooperation.

ai philosophy self-learning morality ai-agents algorithms-and-data-structures goal-setting logical-programming ai-alignment ethics-in-ai ai-transparency

UpdatedNov 2, 2025

tine-mukodza /ai-interview-transparency-hci

Star0

Human-centered AI interview prototype that generates follow-up questions and lets participants rate fairness, relevance, comfort, and trust.

hci explainable-ai systems-design human-centered-ai streamlit ai-transparency

UpdatedDec 15, 2025
Python

The-Human-Channel /the-human-channel-site

Star0

Official website and thought leadership platform for The Human Channel.

ai ai-safety ai-ethics ai-regulation ai-governance ai-personalization ai-transparency ai-identity consent-first-ai human-in-the-loop-ai

UpdatedJun 7, 2025
TypeScript

Mindful-AI-Assistants /7-social-buzz-ai-Black-Box-Models--in-AI--Data-Science

Sponsor

Star0

🪐 7- Social Buss: A black box model is an AI or machine learning system whose internal decision-making processes are hidden, providing only inputs and outputs without revealing how outcomes are derived. These models offer high accuracy for complex tasks but pose challenges for interpretability and trust.

machinelearning lime xai shap blackbox-models modelinterpretability ai-transparency