Siddique, Zara ![]() ![]() ![]() ![]() |
Preview |
PDF
- Published Version
Available under License Creative Commons Attribution. Download (5MB) | Preview |
Abstract
We introduce *Dialz*, a Python library for advancing research on steering vectors for open-source LMs. Steering vectors allow users to modify activations at inference time to amplify or weaken a ‘concept’, e.g. honesty or positivity, providing a more powerful alternative to prompting or fine-tuning. Dialz supports a diverse set of tasks, including creating contrastive pair datasets, computing and applying steering vectors, and visualizations. Unlike existing libraries, Dialz emphasizes modularity and usability, enabling both rapid prototyping and in-depth analysis. We demonstrate how Dialz can be used to reduce harmful outputs such as stereotypes, while also providing insights into model behaviour across different layers. We release Dialz with full documentation, tutorials, and support for popular open-source models to encourage further research in safe and controllable language generation. Dialz enables faster research cycles and facilitates insights into model interpretability, paving the way for safer, more transparent, and more reliable AI systems.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Date Type: | Publication |
Status: | Published |
Schools: | Schools > Computer Science & Informatics |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
Publisher: | Association for Computational Linguistics |
ISBN: | 979-8-89176-253-4 |
Date of First Compliant Deposit: | 25 July 2025 |
Date of Acceptance: | 1 June 2025 |
Last Modified: | 01 Aug 2025 10:00 |
URI: | https://orca.cardiff.ac.uk/id/eprint/180025 |
Actions (repository staff only)
![]() |
Edit Item |