AACL2026 Findings Edit Robustness Under Fine-Tuning in Text-to-Image Models
Feng He, Marco Valentino, Zhixue Zhao
AACL2026 Findings Think When Unsure: Leveraging Model Confidence to Decide When to Use Chain-of-Thought
Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras
AACL2026 Findings From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks
Ayan Datta, Mounika Marreddy, Alexander Mehler, Zhixue Zhao, Radhika Mamidi
ECIR2025 Do LLMs Provide Consistent Answers to Health-Related Questions Across Languages?
Ipek Baris Schlicht, Zhixue Zhao, Burcu Sayin, Lucie Flek, Paolo Rosso
TACL2024 Vol. 12 Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization.
George Chrysostomou, Zhixue Zhao, Miles Williams, Nikolaos Aletras.
NAACL 2024 Main (oral presentation) Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models.
Zhixue Zhao, Nikolaos Aletras
JAMIA Vol.7 4(2024) The FAIR database: facilitating access to public health research literature.
Zhixue Zhao, James Thomas, Gregory Kell, Claire Stansfield, Mark Clowes, Sergio Graziosi, Jeff Brunton, Iain James Marshall, Mark Stevenson.
ReLM@AAAI24 Use ReAGent via Inseq ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models.
Zhixue Zhao, Boxuan Shan. 2024.
ACL 2023 Main [Oral (the 1st talk was ours)] Incorporating Attribution Importance for Improving Faithfulness Metrics.
Zhixue Zhao, Nikolaos Aletras
EMNLP 2022 Findings On the Impact of Temporal Concept Drift on Model Explanations.
Zhixue Zhao, George Chrysostomou, Kalina Bontcheva, Nikolaos Aletras
Online Social Networks and Media 2022 Utilizing Subjectivity Level to Mitigate Identity Term Bias in Toxic Comments Classification.
Zhixue Zhao, Ziqi Zhang, Frank Hopfgartner
WWW2021 Companion A Comparative Study of Using Pre-trained Language Models for Toxic Comment Classification.
Zhixue Zhao, Ziqi Zhang, Frank Hopfgartner
CICLing 2019 Detecting Toxic Content Online and the Effect of Training Data on Classification Performance.
Zhixue Zhao, Ziqi Zhang, Frank Hopfgartner