Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial
factors to achieve success is aligning the LLM's output with human preferences. This …

Inference-time alignment enhances the performance of large language models without
requiring additional training or fine-tuning but presents challenges due to balancing …

Aligning large language models (LLMs) with human preferences is critical for their
deployment. Recently, decoding-time alignment has emerged as an effective plug-and-play …

Large language models are typically fine-tuned to align with human preferences, but tuning
large models is computationally intensive and complex. In this work, we introduce $\textit …

In this perspective paper, we introduce the concept of Specialized Generalist Artificial
Intelligence (SGAI or simply SGI) as a crucial milestone toward Artificial General Intelligence …

As generative AI, particularly large language models (LLMs), become increasingly
integrated into production applications, new attack surfaces and vulnerabilities emerge and …

Aligning language models with human preferences is crucial for reducing errors and biases
in these models. Alignment techniques, such as reinforcement learning from human …

Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs)
is a challenging problem as human preferences are complex, multifaceted, and often …

While large language models (LLMs) have seen unprecedented advancements in
capabilities and applications across a variety of use-cases, safety alignment of these models …

This paper examines the challenges associated with achieving life-long superalignment in
AI systems, particularly large language models (LLMs). Superalignment is a theoretical …