4 papers
Post-training Large Language Models for Diverse High-Quality Responses
Yilei Chen, Souradip Chakraborty, Lorenz Wolf +2
Reinforcement learning (RL) has emerged as a popular method for post-training large language models (LLMs). While improving the model's performance on downstream tasks, it often re…
Reward Model Overoptimisation in Iterated RLHF
Lorenz Wolf, Robert Kirk, Mirco Musolesi
Reinforcement learning from human feedback (RLHF) is a widely used method for aligning large language models with human preferences. However, RLHF often suffers from reward model o…
This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs
Lorenz Wolf, Sangwoong Yoon, Ilija Bogunovic
Mixture of large language model (LLMs) Agents (MoA) architectures achieve state-of-the-art performance on prominent benchmarks like AlpacaEval 2.0 by leveraging the collaboration o…
Private Selection with Heterogeneous Sensitivities
Daniela Antonova, Allegra Laro, Audra McMillan +1
Differentially private (DP) selection involves choosing a high-scoring candidate from a finite candidate pool, where each score depends on a sensitive dataset. This problem arises…