Wenfang Wu

Wenfang Wu

Auto-generated profile, based on publicly available information

Wenfang Wu


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
17 April 2025 in Information Fusion
Verified
Journal Article
Closed access
XYXiaocui Yang
Xiaocui Yang
WWWenfang Wu
Wenfang Wu
SFShi Feng
Shi Feng
MWMing Wang
Ming Wang
DWDaling Wang
Daling Wang
SPSoujanya Poria
Soujanya Poria

31 January 2026 in Journal of Artificial Intelligence Research
Verified
Journal Article
Closed access
PDF file
MWMing Wang
Ming Wang
DWDaling Wang
Daling Wang
WWWenfang Wu
Wenfang Wu
SFShi Feng
Shi Feng
YZYifei Zhang
Yifei Zhang
To address the interpretability challenge in machine learning (ML) systems, counterfactual explanations (CEs) have emerged as a promising solution. CEs are unique as they provide workable suggestions to users, instead of explaining why a certain outcome was predicted. The application of CEs encounters two main challenges: general user preferences and variable ML systems. On one hand, user preferences for specific values can vary depending on the task and scenario. On the other hand, the ML systems for verification may change while the CEs are performed. Thus, user preferences tend to be general rather than specific, and CEs need to be adaptable to variable ML models while maintaining robustness even as these models change. Facing these challenges, we propose general user preferences based on insights from psychology and behavioral science, and add the challenge of non-static ML systems as one preference. Moreover, we introduce a novel method, Tree-based Conditions Optional Links (T-COL) for generating CEs adaptable to general user preferences. Moreover, we employ T-COL to enhance the robustness of CEs with specific conditions, making CEs robust even when the ML models are replaced. To assess subjectivity preferences, we define LLM-based autonomous agents to simulate users and align them with real users. Experiments show that T-COL outperforms all baselines in adapting to general user preferences.