Owlstown Text-Only

Ruta Binkyte

Post Doc Researcher

Go to full site

Home

About

Service

Galleries

Posts

Hi!

I'm a postdoctoral researcher in AI Ethics and Safety at the Helmholtz Centre for Information Security (CISPA). My background includes Social Anthropology and Computer Science, which helps me to tackle complex socio-technical trade-offs in AI. My research develops causal and interactional foundations for trustworthy AI. I study how fairness, safety, and accountability emerge in socio-technical systems. I have recently moved from causal fairness in predictive models to generative AI and multi-agent, agentic systems. My current work focuses on formal frameworks for supervising collaborative AI systems through communication, internal representations, and actions.
Check out my latest publications below ↓

My Latest Publications

Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models

Ruta; Binkyte, Ivaxi; Sheth, Zhijing; Jin, Mohammad; Havaei, Bernhard; Schölkopf, Mario Fritz

2025

Interactional Fairness in LLM Multi-Agent Systems: An Evaluation Framework

Ruta Binkyte

AAAI/ACM AIES, 2025, Oral Presentation, 2025

Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews

Sai Suresh Marchala Vasu, Ivaxi Sheth, Hui-Po Wang, Ruta Binkyte, Mario Fritz

arXiv preprint arXiv:2509.13400, 2025

Safety is Essential for Responsible Open-Ended Systems

Ivaxi; Sheth, Jan; Wehner, Sahar; Abdelnabi, Ruta; Binkyte, Mario Fritz

2025

More Publications

Highlights

Oct 9, 2024

Advisory Board Member Savannah Digital Research Institute

Sep 9, 2024

Chair for Diversity and Inclusion ECML'24 Conference, Vilnius

Oct 9, 2021

Women Tech Makers (WTM) Google Scholar Award