arXiv AI By Leah Davis, Dominic Martin, AJung Moon

A Chain Is Only as Strong as Its Weakest Link: A Scoping Review of System Integration Audits in AI

Read the original on arXiv AI →

arXiv:2608. 04921v1 Announce Type: cross Abstract: As AI systems become increasingly integrated into diverse interfaces and applications, model-centric audits are insufficient to address risks arising from interactions among system components and deployment environments.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 2

Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing

arXiv:2606. 00033v1 Announce Type: cross Abstract: While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments.

By Michael Lan, Narmeen Fatimah Oozeer, Chaithanya Bandi, Philip Quirke, Austin Meek, Fazl Barez, Amirali Abdullah
arXiv AI
Jul 1

FLARE-AI: Flaw Reporting for AI

arXiv:2606. 31567v1 Announce Type: cross Abstract: Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety.

By Shayne Longpre, Elaine Zhu, Carson Ezell, Avijit Ghosh, Sean McGregor, Kevin Paeth, Kevin Klyman, Sayash Kapoor, Rishi Bommasani, Ruth Appel, Gregory Strom, Lauren McIlvenny, Mark M. Jaycox, Peter Slattery, Nathan Butters, Arvind Narayanan, Percy Liang, Alex Pentland