Large Language Models (LLMs) went from non-existent to ubiquitous in the machine
learning discourse within a few years. Due to the fast pace of the field, it is difficult to identify …

Reinforcement learning (RL) has achieved tremendous success in many complex decision
making tasks. When it comes to deploying RL in the real world, safety concerns are usually …

Abstract Trustworthy Artificial Intelligence (AI) is based on seven technical requirements
sustained over three main pillars that should be met throughout the system's entire life cycle …

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems
to align with human goals. RLHF has emerged as the central method used to finetune state …

Language Models (LMs) often cannot be deployed because of their potential to harm users
in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using …

Abstract Out-of-distribution (OOD) detection is vital to safety-critical machine learning
applications and has thus been extensively studied, with a plethora of methods developed in …

Artificial agents have traditionally been trained to maximize reward, which may incentivize
power-seeking and deception, analogous to how next-token prediction in language models …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

Large language models (LLMs) show impressive abilities via few-shot prompting.
Commercialized APIs such as OpenAI GPT-3 further increase their use in real-world …

Large-scale pre-training has recently emerged as a technique for creating capable, general-
purpose, generative models such as GPT-3, Megatron-Turing NLG, Gopher, and many …