Towards algorithm auditing: A research overview 👉 https://lnkd.in/ehvspdxY Like financial audits, algorithm audits are becoming the norm in AI. However, this success heavily depends on how effectively it is systematised, scaled, and standardised. In a recent paper, Holistic AI leverages multidisciplinary expertise and practical, real-world insights to present an iterative framework for algorithm auditing with four key dimensions, as seen in the figure below. Adriano Soares Koshiyama, Airlie Hilliard, Siddhant Chatterjee and Emre Kazim give us an overview in this blog post. Karine Perset Celine Caira Luis Aranda Jamie Berryhill Lucia Russo Noah Oder John Leo Tarver ⒿⓁⓉ Rashad Abelson Angélina Gentaz Valéria Silva Bénédicte Rispal Johannes Leon Kirnberger Eunseo Dana Choi Pablo Gomez Ayerbe Sara Fialho Esposito Nikolas S. Sarah Bérubé Guillermo H. #algorithms #audits #artificialintelligence #trustworthyai #aipolicy
Great to see new work in the field of algorithmic auditing, looking forward to reading this!
PhD in Machine Learning. Consultant. Current focus: AI Governance, EU AI Act, Multi-agent LLMs (opinions my own)
3moVery nice article and... may I also place a shameless plug here to point out the connection to our recently published paper on the same subject 😊? https://arxiv.org/abs/2405.13191