![Zara Siddique](https://profiles-cardiff.imgix.net/attachments/6483?w=200&h=200&auto=format&crop=faces&fit=crop&q=90")
Trosolwyg
Rwy'n ymgeisydd PhD yn yr Ysgol Cyfrifiadureg a Gwybodeg, wedi'i ariannu gan AIMLAC CDT. Mae fy thesis yn archwilio sut y gallwn gysyniadu a meintioli niwed a achosir gan fodelau iaith mawr (LLM) a sut mae dulliau debydol yn effeithio ar ffurfiau croestoriadol o wahaniaethu, e.e. hil a rhyw.
Mae fy mhrif ddiddordebau ymchwil ym meysydd rhagfarn mewn moeseg LLM ac AI, yn ogystal â thuedd gwleidyddol a chyfryngol. Rwyf hefyd yn aelod o grŵp ymchwil NLP Caerdydd .
Cyhoeddiad
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 2025Proceedings 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.
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 2024Proceedings 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)
Cynadleddau
- 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 2025Proceedings 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.
- 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 2024Proceedings 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)
Goruchwylwyr
Contact Details
Themâu ymchwil
Arbenigeddau
- Moeseg AI
- Prosesu iaith naturiol