6 accepted papers
Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety. Yet the AI reporting ecosystem is fragmented: researchers who identify flaws often do not know what or where to report, and groups who receive reports rarely share them with other relevant s…
As artificial intelligence (AI) systems become increasingly deployed across the world, they are also increasingly implicated in AI incidents – harm events to individuals and society. As a result, industry, civil society, and governments worldwide are developing best practices and regulations for mon…
The widespread deployment of general-purpose AI (GPAI) systems introduces significant new risks. Yet the infrastructure, practices, and norms for reporting flaws in GPAI systems remain seriously underdeveloped, lagging far behind more established fields like software security. Based on a collaborati…
Large language model (LLM) benchmarks inform LLM use decisions (e.g., "is this LLM safe to deploy for my use case and context?"). However, benchmarks may be rendered unreliable by various failure modes impacting benchmark bias, variance, coverage, or people's capacity to understand benchmark evidenc…
In August of 2024, 495 hackers generated evaluations in an open-ended bug bounty targeting the Open Language Model (OLMo) from The Allen Institute for AI. A vendor panel staffed by representatives of OLMo's safety program adjudicated changes to OLMo's documentation and awarded cash bounties to parti…
Intelligent system audits are labor-intensive assurance activities that are typically performed once and discarded along with the opportunity to programmatically test all similar products for the market. This study illustrates how several incidents (i.e., harms) involving Named Entity Recognition (N…