Grounding and evaluation for large language models: Practical challenges and lessons learned (survey)
With the ongoing rapid adoption of Artificial Intelligence (AI)-based systems in high-stakes
domains, ensuring the trustworthiness, safety, and observability of these systems has …
domains, ensuring the trustworthiness, safety, and observability of these systems has …
Infecting Generative AI With Viruses
This study demonstrates a novel approach to testing the security boundaries of Vision-Large
Language Model (VLM/LLM) using the EICAR test file embedded within JPEG images. We …
Language Model (VLM/LLM) using the EICAR test file embedded within JPEG images. We …
Measurement challenges in AI catastrophic risk governance and safety frameworks
A Kasirzadeh - arxiv preprint arxiv:2410.00608, 2024 - arxiv.org
Safety frameworks represent a significant development in AI governance: they are the first
type of publicly shared catastrophic risk management framework developed by major AI …
type of publicly shared catastrophic risk management framework developed by major AI …