Scholar
Wei Liu
Google Scholar ID: bG4dvGoAAAAJ
National University of Singapore
Citations & Impact
Citations
160
H-index
8
i10-index
6
Publications
16
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Paper: Is Model Editing Built on Sand? Revealing Its Illusory Success and Fragile Foundation
- Paper: Unbiased Interest Modeling in Sequential Basket Analysis: Addressing Repetition Bias with Multi-Factor Estimation, In TORS 2025
- Paper: Re-fed+: A better replay strategy for federated incremental learning, In TPAMI 2025
- Paper: Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets, Conference: ICML 2025
- Paper: Exploring Practical Gaps in Using Cross Entropy to Implement Maximum Mutual Information Criterion for Rationalization, In TACL 2025
- Paper: Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization, Conference: ICLR 2025
- Paper: Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization, Conference: NeurIPS 2024
- Paper: Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling, Conference: AAAI 2024
- Paper: Enhancing the Rationale-Input Alignment for Self-explaining Rationalization, Conference: ICDE 2024
- Paper: D-Separation for Causal Self-Explanation, Conference: NeurIPS 2023
- Paper: Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint, Conference: KDD 2023
- Paper: MGR: Multi-generator Based Rationalization, Conference: ACL 2023 (Oral, Top 4%)
- Paper: Multi-view Multi-aspect Neural Networks for Next-Basket Recommendation, Conference: SIGIR 2023
- Paper: FR: Folded Rationalization with a Unified Encoder, Conference: NeurIPS 2022
Background
- Currently a research fellow at National University of Singapore, focusing on machine learning and natural language processing. Recent research has been concentrating on various issues related to large language models.
Co-authors