AI Safety Evaluations Need To Consider Cascading Effects

TL;DR

This paper emphasizes the importance of considering cascading effects in AI safety evaluations, highlighting how interactions within socio-technical supply chains can lead to compounded downstream consequences.

Contribution

It introduces the concept of cascades for holistic AI evaluations, identifying gaps in current auditing methods and proposing new research directions.

Findings

Cascades can significantly impact AI safety and accountability.

Current evaluations often overlook interaction effects in socio-technical systems.

Research directions for assessing cascades are outlined.

Abstract

AI systems comprise a range of interactions across the technical and organisational components of a range of actors. These components work together to provide the systems' functionality. This socio-technical assemblage is increasingly described as an algorithmic supply chain. Given their role in supporting a wide range of systems, foundation models (FMs) are increasingly a key part of many algorithmic supply chains. In practice, various technical and non-technical components work to mediate, adapt, and augment the behaviour of models, such as FMs, both in general, and for their use in specific application contexts. However, many AI safety evaluations tend to focus on capabilities of FMs themselves and/or assess these components independently, at certain levels of abstraction, with less consideration on how these components could interact, influence, reinforce or counteract each other. In this paper, we introduce the cascade as a concept for supporting more holistic AI evaluations. The cascade captures how the interactions between socio-technical components along the AI supply chain can compound and produce cumulative effects with downstream consequences. Specifically, we (i) identify gaps in current AI auditing approaches, using LLMs as our case study; (ii) demonstrate how cascade problems manifest in deployed AI systems through a characterisation of cascades through different viewpoints (component and stakeholder), and (iii) propose research directions for assessing the cascade specifically as an object of analysis. As these cascades can significantly impact transparency, accountability, security, and safety, we advocate for a paradigm shift in AI system auditing towards systems-oriented audits that incorporate cascading effects, to complement model centric evaluations.