George Chrysostomou

According to our database, George Chrysostomou authored at least 12 papers between 2021 and 2026.

Collaborative distances:

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

2026

Compressing Language Models for Specialized Domains.

Miles Williams, George Chrysostomou, Vitor Jeronymo, Nikolaos Aletras

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

2025

Self-calibration for Language Model Quantization and Pruning.

Miles Williams, George Chrysostomou, Nikolaos Aletras

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

2024

Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization.

George Chrysostomou, Zhixue Zhao, Miles Williams, Nikolaos Aletras

Trans. Assoc. Comput. Linguistics, 2024

2023

Lighter, yet More Faithful: Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization.

George Chrysostomou, Zhixue Zhao, Miles Williams, Nikolaos Aletras

CoRR, 2023

2022

Explainable Natural Language Processing.

George Chrysostomou

Comput. Linguistics, 2022

On the Impact of Temporal Concept Drift on Model Explanations.

Zhixue Zhao, George Chrysostomou, Kalina Bontcheva, Nikolaos Aletras

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

An Empirical Study on Explanations in Out-of-Domain Settings.

George Chrysostomou, Nikolaos Aletras

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

Flexible Instance-Specific Rationalization of NLP Models.

George Chrysostomou, Nikolaos Aletras

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Variable Instance-Level Explainability for Text Classification.

George Chrysostomou, Nikolaos Aletras

CoRR, 2021

Frustratingly Simple Pretraining Alternatives to Masked Language Modeling.

Atsuki Yamaguchi, George Chrysostomou, Katerina Margatina, Nikolaos Aletras

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience.

George Chrysostomou, Nikolaos Aletras

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification.

George Chrysostomou, Nikolaos Aletras

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021