← Authors

George Chrysostomou

9 papers · 2021–2026 · 6 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (12) 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (5) πŸ—ΊοΈ Taxonomy Completionist (16) πŸ“ˆ Trend Setter

Conferences

EMNLP (3) ACL (2) AAAI (1) EACL (1) IJCNLP (1) NAACL (1)

Top co-authors

Nikolaos Aletras (9) Miles Williams (2) Zhixue Zhao (1) Katerina Margatina (1) Kalina Bontcheva (1) Atsuki Yamaguchi (1) Vitor Amancio Jeronymo (1)

Research topics

Understanding (1)

Keywords

text classification (4) attention mechanism (3) feature attribution (3) faithful explanation (2) model interpretability (2) model explanation (2) rationale extraction (1) token classification (1) model pruning (1) language model (1) synthetic datum (1) post-hoc explanation (1) masked language modeling (1) explanation faithfulness (1) calibration method (1) faithfulness evaluation (1) task-specific information (1) transformer-based model (1) calibration datum (1) text rank (1)

Papers

Compressing Language Models for Specialized Domains EACL 2026
Self-calibration for Language Model Quantization and Pruning NAACL 2025
Flexible Instance-Specific Rationalization of NLP Models AAAI 2022
An Empirical Study on Explanations in Out-of-Domain Settings ACL 2022
On the Impact of Temporal Concept Drift on Model Explanations EMNLP 2022
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification ACL 2021
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification IJCNLP 2021
Frustratingly Simple Pretraining Alternatives to Masked Language Modeling EMNLP 2021
Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience EMNLP 2021