← Search

Lauren Alvarez

2 accepted papers

2026

Steering Embedding Models with Geometric Rotation: Mapping Semantic Relationships Across Languages and Models

ICLR 2026poster

Understanding how language and embedding models encode semantic relationships is fundamental to model interpretability. While early word embeddings exhibited intuitive vector arithmetic (''king'' - ''man'' + ''woman'' = ''queen''), modern high-dimensional text representations lack straightforward…

Cited by 0SourceScholar
2024

Performative Ethics From Within the Ivory Tower: How CSPractitioners Uphold Systems of Oppression (Abstract Reprint)

IJCAI 2024poster

This paper analyzes where Artificial Intelligence (AI) Ethics research fails and breaks down the dangers of well-intentioned, but ultimately performative ethics research. A large majority of AI ethics research is critiqued for lacking a comprehensive analysis of how AI is interconnected with sociolo…

Cited by 0SourcePDFScholar