← Search

Savvas Petridis

2 accepted papers

2025

Position: Towards Bidirectional Human-AI Alignment

NeurIPS 2025poster

Recent advances in general-purpose AI underscore the urgent need to align AI systems with human goals and values. Yet, the lack of a clear, shared understanding of what constitutes "alignment" limits meaningful progress and cross-disciplinary collaboration. In this position paper, we argue that the…

Cited by 0SourceScholar
2024

ConstitutionalExperts: Training a Mixture of Principle-based Prompts

ACL 2024short

Large language models (LLMs) are highly capable at a variety of tasks given the right prompt, but writing one is still a difficult and tedious process. In this work, we introduce ConstitutionalExperts, a method for learning a prompt consisting of constitutional principles (i.e. rules), given a train…

Cited by 6SourcePDFScholar