A.J. (Alina) Leidinger MSc
Faculteit der Natuurwetenschappen, Wiskunde en Informatica
ILLC
Bezoekadres
- Science Park 900
- Kamernummer: L6.53
Postadres
-
Postbus 94242
1090 GE Amsterdam
Contactgegevens
-
Publicaties
- refereed (4)
- wetenschappelijk (1)
- congresbijdragen (2)
- erkenning (4)
- working papers / preprints (1)
- datasets (2)
2024
Leidinger, A. J., & Rogers, R. A. (2024). How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (Vol. 7, pp. 839-854). AAAI Press.- van der Wal, O., Bachmann, D., Leidinger, A., van Maanen, L., Zuidema, W., & Schulz, K. (2024). Undesirable Biases in NLP: Addressing Challenges of Measurement. Journal of Artificial Intelligence Research, 79, 1-40. https://doi.org/10.1613/jair.1.15195 [details]
2023
- Leidinger, A., & Rogers, R. (2023). Which Stereotypes Are Moderated and Under-Moderated in Search Engine Autocompletion? In FAccT '23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency (pp. 1049–1061). Association for Computing Machinery. https://doi.org/10.1145/3593013.3594062 [details]
- Starace, G., Papakostas, K., Choenni, R., Panagiotopoulos, A., Rosati, M., Leidinger, A., & Shutova, E. (2023). Probing LLMs for Joint Encoding of Linguistic Categories. In H. Bouamor, J. Pino, & K. Bali (Eds.), The 2023 Conference on Empirical Methods in Natural Language Processing : Findings of the Association for Computational Linguistics: EMNLP 2023: December 6-10, 2023 (pp. 7158-7179). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-emnlp.476 [details]
2022
- van der Wal, O., Bachmann, D., Leidinger, A., van Maanen, L., Zuidema, W., & Schulz, K. (2022). Undesirable biases in NLP: Averting a crisis of measurement. (v1 ed.) ArXiv. https://doi.org/10.48550/arXiv.2211.13709 [details]
2024
- Leidinger, A. J., van Rooij, R. A. M., & Shutova, E. V. (2024). Are LLMs classical or nonmonotonic reasoners? Lessons from generics. Paper presented at The 62nd Annual Meeting of the Association for Computational Linguistics. https://aclanthology.org/2024.acl-short.51/
2023
- Leidinger, A. J., van Rooij, R. A. M., & Shutova, E. V. (2023). The Language of Prompting: What linguistic properties make a prompt successful?. https://arxiv.org/abs/2311.01967
Spreker
- Leidinger, A. (speaker) (2023). How safe are LLMs compared to search engine autocompletions? A bias check-up, Workshop @ Comète on Ethical AI. https://www.lix.polytechnique.fr/ethicalai/presentations/alina-leidinger/
- Leidinger, A. (speaker) (2023). Stereotypes in LLMs, Workshop on generative AI and search engines at HAW, Hamburg..
Andere
- Leidinger, A. (participant) (19-9-2022 - 23-9-2022). ELLIS PhD symposium, Alicante (participating in a conference, workshop, ...).
- Leidinger, A. (participant) (2022 - 2024). Computational Linguistics Seminar (CLS), ILLC, UvA, Amsterdam (organising a conference, workshop, ...).
2022
- Leidinger, A. J. (2022). Generating stereotypes from implicitly hateful posts.
2023
- Leidinger, A. & Rogers, R. (8-5-2023). Stereotype elicitation in Google, DuckDuckGo and Yahoo! autcompletion. Zenodo. https://doi.org/10.5281/zenodo.7906930
- Leidinger, A. (2023). Code for preprint Generating stereotypes from implicitly hateful posts. Universiteit van Amsterdam.
This list of publications is extracted from the UvA-Current Research Information System. Questions? Ask the library or the Pure staff of your faculty / institute. Log in to Pure to edit your publications. Log in to Personal Page Publication Selection tool to manage the visibility of your publications on this list. -
Nevenwerkzaamheden
Geen nevenwerkzaamheden
Leidinger, A. J., & Rogers, R. A. (2024). How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (Vol. 7, pp. 839-854). AAAI Press.