4 papers
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…
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…
Automatic Extraction of Metaphoric Analogies from Literary Texts: Task Formulation, Dataset Construction, and Evaluation
Joanne Boisson, Zara Siddique, Hsuvas Borkakoty +3
Extracting metaphors and analogies from free text requires high-level reasoning abilities such as abstraction and language understanding. Our study focuses on the extraction of the…
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…