Miriam Rateike

Bio

HI! I work at IBM Research Africa in the Nairobi lab. I am interested in trustworthy ML, especially interpretability of large generative models and regulation.

Publications

Localizing Persona Representations in LLMs
- - Celia Cintas
  - Miriam Rateike
  - et al.
- 2025
- AIES 2025
Localizing Persona Representations in LLMs
- - Celia Cintas
  - Miriam Rateike
  - et al.
- 2025
- COLM 2025
The Impact of Domain Adaptation on the Activation Space of LLMs
- - Assala Benmalek
  - Celia Cintas
  - et al.
- 2025
- DLI 2025
3rd TrustAI Workshop: Building Public Awareness and Engagement
- - Miriam Rateike
  - Brian Mboya
  - et al.
- 2025
- DLI 2025
Robustness and Cybersecurity in the EU Artificial Intelligence Act
- - Henrik Nolte
  - Miriam Rateike
  - et al.
- 2025
- FAccT 2025
Weakly Supervised Detection of Hallucinations in LLM Activations
- - Miriam Rateike
  - Celia Cintas
  - et al.
- 2023
- NeurIPS 2023

Projects

Deep Scanner
A tale of adversarial attacks & out-of-distribution detection stories in the activation space

Top collaborators

Skyler Speakman

Senior Research Scientist, First line manager

Celia Cintas

Staff Research Scientist

Elizabeth Daly

STSM, Research Manager, Interactive AI Group

Erik Miehling

Staff Research Scientist