A comparative study of using pre-trained language models for toxic comment classification Z Zhao, Z Zhang, F Hopfgartner Companion Proceedings of the Web Conference 2021, 500-507, 2021 | 38 | 2021 |
On the Impact of Temporal Concept Drift on Model Explanations Z Zhao, G Chrysostomou, K Bontcheva, N Aletras The 2022 Conference on Empirical Methods in Natural Language Processing …, 2022 | 8 | 2022 |
SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of" Subjectivity" and" Identity Terms" Z Zhao, Z Zhang, F Hopfgartner arXiv preprint arXiv:2109.02691, 2021 | 7 | 2021 |
Detecting toxic content online and the effect of training data on classification performance Z Zhao, Z Zhang, F Hopfgartner CICLing 2019, 2019 | 6 | 2019 |
Incorporating Attribution Importance for Improving Faithfulness Metrics Z Zhao, A Nikolaos 61st Annual Meeting of the Association for Computational Linguistics 1 (Long …, 2023 | 5 | 2023 |
Utilizing subjectivity level to mitigate identity term bias in toxic comments classification Z Zhao, Z Zhang, F Hopfgartner Online Social Networks and Media 29, 100205, 2022 | 2 | 2022 |
Using Pre-trained Language Models for Toxic Comment Classification Z Zhao University of Sheffield, 2022 | 2 | 2022 |
Detecting Edited Knowledge in Language Models P Youssef, Z Zhao, J Schlötterer, C Seifert arXiv preprint arXiv:2405.02765, 2024 | | 2024 |
Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models Z Zhao, N Aletras NAACL 2024, 2024 | | 2024 |
ReAGent: Towards A Model-agnostic Feature Attribution Method for Generative Language Models Z Zhao, B Shan ReLM at AAAI24, 2024 | | 2024 |
Lighter, yet More Faithful: Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization G Chrysostomou, Z Zhao, M Williams, N Aletras arXiv preprint arXiv:2311.09335, 2023 | | 2023 |