Hannah Cyberey

According to our database, Hannah Cyberey authored at least 7 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control.

Hannah Cyberey, David Evans

CoRR, April, 2025

Sensing and Steering Stereotypes: Extracting and Applying Gender Representation Vectors in LLMs.

Hannah Cyberey, Yangfeng Ji, David Evans

CoRR, February, 2025

2024

The Mismeasure of Man and Models: Evaluating Allocational Harms in Large Language Models.

Hannah Chen, Yangfeng Ji, David Evans

CoRR, 2024

Addressing Both Statistical and Causal Gender Fairness in NLP Models.

Hannah Chen, Yangfeng Ji, David Evans

Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2024, 2024

2022

Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models.

Hannah Chen, Yangfeng Ji, David E. Evans

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

2020

Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory.

Hannah Chen, Yangfeng Ji, David E. Evans

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

Pointwise Paraphrase Appraisal is Potentially Problematic.

Hannah Chen, Yangfeng Ji, David Evans

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, 2020