![Zara Siddique](https://profiles-cardiff.imgix.net/attachments/6483?w=200&h=200&auto=format&crop=faces&fit=crop&q=90")
Zara Siddique
(she/her)
Teams and roles for Zara Siddique
Research Associate
Overview
I am a Research Associate on the SWEET project based in The Centre for Social Care and Artificial Intelligence Learning (SCALE).
My main research interests lie in the fields of AI in social care, bias in LLMs and AI ethics, as well as political and media bias. I am also a member of the Cardiff NLP research group.
Publication
2026
- Siddique, Z. et al. 2026. Shifting perspectives: Steering vectors for robust bias mitigation in LLMs. Presented at: European Chapter of the Association for Computational Linguistics (EACL 2026) Rabat, Morocco 24-29 March 2026. Published in: Demberg, V. , Inui, K. and Marquez, L. eds. Findings of the Association for Computational Linguistics: EACL 2026. Rabat, Morocco: Association for Computational Linguistics. , pp.809-820. (10.18653/v1/2026.findings-eacl.41)
2025
- Siddique, Z. , Turner, L. and Espinosa-Anke, L. 2025. Dialz: A Python toolkit for steering vectors. Presented at: The 63rd Annual Meeting of the Association for Computational Linguistics Vienna, Austria 27 July - 1 August 2025. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Vol. 3.Vienna, Austria: Association for Computational Linguistics. , pp.363-375. (10.18653/v1/2025.acl-demo.35)
- Siddique, Z. 2025. Measuring and mitigating stereotypes in large language models. PhD Thesis , Cardiff University.
2024
- Siddique, Z. , Turner, L. and Espinosa-Anke, L. 2024. Who is better at math, Jenny or Jingzhen? Uncovering Stereotypes in Large Language Models. Presented at: The 2024 Conference on Empirical Methods in Natural Language Processing Miami, FL, USA 12-16 November 2024. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. , pp.18601-18619. (10.18653/v1/2024.emnlp-main.1035)
Conferences
- Siddique, Z. et al. 2026. Shifting perspectives: Steering vectors for robust bias mitigation in LLMs. Presented at: European Chapter of the Association for Computational Linguistics (EACL 2026) Rabat, Morocco 24-29 March 2026. Published in: Demberg, V. , Inui, K. and Marquez, L. eds. Findings of the Association for Computational Linguistics: EACL 2026. Rabat, Morocco: Association for Computational Linguistics. , pp.809-820. (10.18653/v1/2026.findings-eacl.41)
- Siddique, Z. , Turner, L. and Espinosa-Anke, L. 2025. Dialz: A Python toolkit for steering vectors. Presented at: The 63rd Annual Meeting of the Association for Computational Linguistics Vienna, Austria 27 July - 1 August 2025. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Vol. 3.Vienna, Austria: Association for Computational Linguistics. , pp.363-375. (10.18653/v1/2025.acl-demo.35)
- Siddique, Z. , Turner, L. and Espinosa-Anke, L. 2024. Who is better at math, Jenny or Jingzhen? Uncovering Stereotypes in Large Language Models. Presented at: The 2024 Conference on Empirical Methods in Natural Language Processing Miami, FL, USA 12-16 November 2024. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. , pp.18601-18619. (10.18653/v1/2024.emnlp-main.1035)
Thesis
- Siddique, Z. 2025. Measuring and mitigating stereotypes in large language models. PhD Thesis , Cardiff University.
Contact Details
Research themes
Specialisms
- AI Ethics
- Natural language processing
- children's social care