Zhixue Zhao

Zhixue Zhao

Auto-generated profile, based on publicly available information

Zhixue Zhao

University of Sheffield

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 March 2022 in Online Social Networks and Media
Verified
Journal Article
Closed access
ZZZhixue Zhao
Zhixue Zhao
ZZZiqi Zhang
Ziqi Zhang
FHFrank Hopfgartner
Frank Hopfgartner

1 January 2024
Verified
Conference Paper
Open access
PDF file
ZZZhixue Zhao
Zhixue Zhao
NANikolaos Aletras
Nikolaos Aletras
Zhixue Zhao, Nikolaos Aletras. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

1 January 2023
Verified
Conference Paper
Open access
PDF file
ZZZhixue Zhao
Zhixue Zhao
NANikolaos Aletras
Nikolaos Aletras
Zhixue Zhao, Nikolaos Aletras. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

4 April 2025
Verified
Book Chapter
Closed access
PDF file
ISIpek Baris Schlicht
Ipek Baris Schlicht
ZZZhixue Zhao
Zhixue Zhao
BSBurcu Sayin
Burcu Sayin
LFLucie Flek
Lucie Flek
PRPaolo Rosso
Paolo Rosso

1 January 2025
Verified
Conference Paper
Open access
PDF file
SLSamuel Lewis-Lim
Samuel Lewis-Lim
XTXingwei Tan
Xingwei Tan
ZZZhixue Zhao
Zhixue Zhao
NANikolaos Aletras
Nikolaos Aletras
Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

5 February 2024
Verified
Preprint
Open access
ZZZhixue Zhao
Zhixue Zhao
BSBoxuan Shan
Boxuan Shan
Feature attribution methods (FAs), such as gradients and attention, are widely employed approaches to derive the importance of all input features to the model predictions. Existing work in natural language processing has mostly focused on developing and testing FAs for encoder-only language models (LMs) in classification tasks. However, it is unknown if it is faithful to use these FAs for decoder-only models on text generation, due to the inherent differences between model architectures and task settings respectively. Moreover, previous work has demonstrated that there is no 'one-wins-all' FA across models and tasks. This makes the selection of a FA computationally expensive for large LMs since input importance derivation often requires multiple forward and backward passes including gradient computations that might be prohibitive even with access to large compute. To address these issues, we present a model-agnostic FA for generative LMs called Recursive Attribution Generator (ReAGent). Our method updates the token importance distribution in a recursive manner. For each update, we compute the difference in the probability distribution over the vocabulary for predicting the next token between using the original input and using a modified version where a part of the input is replaced with RoBERTa predictions. Our intuition is that replacing an important token in the context should have resulted in a larger change in the model's confidence in predicting the token than replacing an unimportant token. Our method can be universally applied to any generative LM without accessing internal model weights or additional training and fine-tuning, as most other FAs require. We extensively compare the faithfulness of ReAGent with seven popular FAs across six decoder-only LMs of various sizes. The results show that our method consistently provides more faithful token importance distributions. Our code: https://github.com/casszhao/ReAGent