Nikolaos Aletras

Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates

Can Confidence Estimates Decide When Chain-of-Thought is Necessary for LLMs?

BusMA: A Bus Communication Substrate for Multi- Agent Systems

Adaptive Uncertainty-Aware Reinforcement Learning from Human Feedback

Multi-Fidelity Fine-Tuning of Pre-Trained Language Models