activity
20242026
collaborators
Showing 2024Show all

35 papers · 1 filter

cs.LG2024

Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes

Katarzyna Kobalczyk, Claudio Fanconi, Hao Sun +1

As large language models (LLMs) become increasingly embedded in everyday applications, ensuring their alignment with the diverse preferences of individual users has become a critic…

cs.LG2024

Quantifying perturbation impacts for large language models

Paulius Rauba, Qiyao Wei, Mihaela van der Schaar

We consider the problem of quantifying how an input perturbation impacts the outputs of large language models (LLMs), a fundamental task for model reliability and post-hoc interpre…

cs.HC2024

CliMB: An AI-enabled Partner for Clinical Predictive Modeling

Evgeny Saveliev, Tim Schubert, Thomas Pouplin +2

Despite its significant promise and continuous technical advances, real-world applications of artificial intelligence (AI) remain limited. We attribute this to the "domain expert-A…

cs.LG2024

Discovering Preference Optimization Algorithms with and for Large Language Models

Chris Lu, Samuel Holt, Claudio Fanconi +4

Offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. Typically, preference optimization is approached as…

cs.LG2024

Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond

Alan Jeffares, Alicia Curth, Mihaela van der Schaar

Deep learning sometimes appears to work in unexpected ways. In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate mo…

cs.LG2024

Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments

Paulius Rauba, Nabeel Seedat, Krzysztof Kacprzyk +1

Real-world machine learning systems often encounter model performance degradation due to distributional shifts in the underlying data generating process (DGP). Existing approaches…