5 papers
Evolutionary Soups: Evolving Mixture-of-Experts for Multi-Objective LLM Alignment
Lingxiao Kong, Steffen Staab, Cong Yang +2
Large language models are increasingly required to generate responses that satisfy multiple competing objectives. Since optimal trade-offs depend on both user preferences and input…
Autonomous FAIR Digital Objects: From Passive Assertions to Active Knowledge
Zeyd Boukhers, Oya Beyan, Cong Yang +1
Scientific knowledge on the Web is published as passive assertions and cannot decide when to validate evidence, reconcile contradictions, or update confidence as findings accumulat…
Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
Lingxiao Kong, Cong Yang, Oya Deniz Beyan +1
Despite significant advances in Reinforcement Learning (RL), model performance remains highly sensitive to algorithm and hyperparameter configurations, while generalization gaps ac…
Multi-Objective Reinforcement Learning for Large Language Model Optimization: Visionary Perspective
Lingxiao Kong, Cong Yang, Oya Deniz Beyan +1
Multi-Objective Reinforcement Learning (MORL) presents significant challenges and opportunities for optimizing multiple objectives in Large Language Models (LLMs). We introduce a M…
EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning
Lingxiao Kong, Cong Yang, Susanne Neufang +2
Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, in…