With the recent Nobel Prize awarded for radical advances in protein discovery, foundation
models (FMs) for exploring large combinatorial spaces promise to revolutionize many …

We present an empirical study investigating how specific properties of preference datasets,
such as mixed-quality or noisy data, affect the performance of Preference Optimization (PO) …

Reinforcement learning from human feedback (RLHF) aligns Large Language Models
(LLMs) with human preferences. However, these preferences can often change over time …

Real-time detection of out-of-context LLM outputs is crucial for enterprises looking to safely
adopt RAG applications. In this work, we train lightweight models to discriminate LLM …

Large Language Models are prone to off-topic misuse, where users may prompt these
models to perform tasks beyond their intended scope. Current guardrails, which often rely on …

The demand for computational power in machine learning has increased exponentially over
the past decade, driven by the rising complexity of deep learning models and the need for …

Multi-agent dynamics have powered innovation from time immemorial, such as scientific
innovations during the space race or predator-prey dynamics in the natural world. The …

The current iterative development process for large language models (LLMs) is heavily data-
centric, relying on human researchers and engineers to manually analyze model …

Large language and foundation models have become ubiquitous as general-purpose
assistants, exhibiting diverse capabilities across a wide variety of domains through training …