A Grading Rubric for AI Safety Frameworks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Alaga, Jide, Schuett, Jonas, Anderljung, Markus
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917775173222400
author Alaga, Jide
Schuett, Jonas
Anderljung, Markus
author_facet Alaga, Jide
Schuett, Jonas
Anderljung, Markus
contents Over the past year, artificial intelligence (AI) companies have been increasingly adopting AI safety frameworks. These frameworks outline how companies intend to keep the potential risks associated with developing and deploying frontier AI systems to an acceptable level. Major players like Anthropic, OpenAI, and Google DeepMind have already published their frameworks, while another 13 companies have signaled their intent to release similar frameworks by February 2025. Given their central role in AI companies' efforts to identify and address unacceptable risks from their systems, AI safety frameworks warrant significant scrutiny. To enable governments, academia, and civil society to pass judgment on these frameworks, this paper proposes a grading rubric. The rubric consists of seven evaluation criteria and 21 indicators that concretize the criteria. Each criterion can be graded on a scale from A (gold standard) to F (substandard). The paper also suggests three methods for applying the rubric: surveys, Delphi studies, and audits. The purpose of the grading rubric is to enable nuanced comparisons between frameworks, identify potential areas of improvement, and promote a race to the top in responsible AI development.
format Preprint
id arxiv_https___arxiv_org_abs_2409_08751
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Grading Rubric for AI Safety Frameworks
Alaga, Jide
Schuett, Jonas
Anderljung, Markus
Computers and Society
Over the past year, artificial intelligence (AI) companies have been increasingly adopting AI safety frameworks. These frameworks outline how companies intend to keep the potential risks associated with developing and deploying frontier AI systems to an acceptable level. Major players like Anthropic, OpenAI, and Google DeepMind have already published their frameworks, while another 13 companies have signaled their intent to release similar frameworks by February 2025. Given their central role in AI companies' efforts to identify and address unacceptable risks from their systems, AI safety frameworks warrant significant scrutiny. To enable governments, academia, and civil society to pass judgment on these frameworks, this paper proposes a grading rubric. The rubric consists of seven evaluation criteria and 21 indicators that concretize the criteria. Each criterion can be graded on a scale from A (gold standard) to F (substandard). The paper also suggests three methods for applying the rubric: surveys, Delphi studies, and audits. The purpose of the grading rubric is to enable nuanced comparisons between frameworks, identify potential areas of improvement, and promote a race to the top in responsible AI development.
title A Grading Rubric for AI Safety Frameworks
topic Computers and Society
url https://arxiv.org/abs/2409.08751