3 papers
cs.LG2026
Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
Zara Siddique, Irtaza Khalid, Liam D. Turner +1
We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes. We compute 8 steering vec…
cs.LG2025
Dialz: A Python Toolkit for Steering Vectors
Zara Siddique, Liam D. Turner, Luis Espinosa-Anke
We introduce Dialz, a framework for advancing research on steering vectors for open-source LLMs, implemented in Python. Steering vectors allow users to modify activations at infere…
cs.CL2024
Who is better at math, Jenny or Jingzhen? Uncovering Stereotypes in Large Language Models
Zara Siddique, Liam D. Turner, Luis Espinosa-Anke
Large language models (LLMs) have been shown to propagate and amplify harmful stereotypes, particularly those that disproportionately affect marginalised communities. To understand…