103 citations · 483 across the 42 of their papers we have counts for
42 papers
Understanding Cognition-Induced Risks in Agentic AI Systems
Guanchu Wang, Qinuo Li, Mengnan Du +2
Frontier agentic systems powered by large language models (LLMs) exhibit human-like patterns of cognition. As these systems become deeply integrated across different domains, their…
FaithLM: Towards Faithful Explanations for Large Language Models
Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang +7
Large language models (LLMs) increasingly produce natural language explanations, yet these explanations often lack faithfulness, and they do not reliably reflect the evidence the m…
TVE: Learning Meta-attribution for Transferable Vision Explainer
Guanchu Wang, Yu-Neng Chuang, Fan Yang +8
Explainable machine learning significantly improves the transparency of deep neural networks. However, existing work is constrained to explaining the behavior of individual model p…
XGBD: Explanation-Guided Graph Backdoor Detection
Zihan Guan, Mengnan Du, Ninghao Liu
Backdoor attacks pose a significant security risk to graph learning models. Backdoors can be embedded into the target model by inserting backdoor triggers into the training dataset…
A Survey on Fairness in Large Language Models
Yingji Li, Mengnan Du, Rui Song +2
Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unpro…
DISPEL: Domain Generalization via Domain-Specific Liberating
Chia-Yuan Chang, Yu-Neng Chuang, Guanchu Wang +2
Domain generalization aims to learn a generalization model that can perform well on unseen test domains by only training on limited source domains. However, existing domain general…
Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases
Yingji Li, Mengnan Du, Xin Wang +1
As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previou…
FAIRER: Fairness as Decision Rationale Alignment
Tianlin Li, Qing Guo, Aishan Liu +3
Deep neural networks (DNNs) have made significant progress, but often suffer from fairness issues, as deep models typically show distinct accuracy differences among certain subgrou…
DEGREE: Decomposition Based Explanation For Graph Neural Networks
Qizhang Feng, Ninghao Liu, Fan Yang +3
Graph Neural Networks (GNNs) are gaining extensive attention for their application in graph data. However, the black-box nature of GNNs prevents users from understanding and trusti…
Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions
Huiqi Deng, Na Zou, Mengnan Du +5
Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the fina…
Black-box Backdoor Defense via Zero-shot Image Purification
Yucheng Shi, Mengnan Du, Xuansheng Wu +3
Backdoor attacks inject poisoned samples into the training data, resulting in the misclassification of the poisoned input during a model's deployment. Defending against such attack…
Efficient XAI Techniques: A Taxonomic Survey
Yu-Neng Chuang, Guanchu Wang, Fan Yang +4
Recently, there has been a growing demand for the deployment of Explainable Artificial Intelligence (XAI) algorithms in real-world applications. However, traditional XAI methods ty…
Mitigating Relational Bias on Knowledge Graphs
Yu-Neng Chuang, Kwei-Herng Lai, Ruixiang Tang +4
Knowledge graph data are prevalent in real-world applications, and knowledge graph neural networks (KGNNs) are essential techniques for knowledge graph representation learning. Alt…
Shortcut Learning of Large Language Models in Natural Language Understanding
Mengnan Du, Fengxiang He, Na Zou +2
Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. However, these LLMs might rely on dataset bias and arti…
Mitigating Algorithmic Bias with Limited Annotations
Guanchu Wang, Mengnan Du, Ninghao Liu +2
Existing work on fairness modeling commonly assumes that sensitive attributes for all instances are fully available, which may not be true in many real-world applications due to th…
Accelerating Shapley Explanation via Contributive Cooperator Selection
Guanchu Wang, Yu-Neng Chuang, Mengnan Du +5
Even though Shapley value provides an effective explanation for a DNN model prediction, the computation relies on the enumeration of all possible input feature coalitions, which le…
Unveiling Project-Specific Bias in Neural Code Models
Zhiming Li, Yanzhou Li, Tianlin Li +5
Deep learning has introduced significant improvements in many software analysis tasks. Although the Large Language Models (LLMs) based neural code models demonstrate commendable pe…
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding
Mengnan Du, Subhabrata Mukherjee, Yu Cheng +3
Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks.…
Fairness via Representation Neutralization
Mengnan Du, Subhabrata Mukherjee, Guanchu Wang +3
Existing bias mitigation methods for DNN models primarily work on learning debiased encoders. This process not only requires a lot of instance-level annotations for sensitive attri…
Learning Disentangled Representations for Time Series
Yuening Li, Zhengzhang Chen, Daochen Zha +4
Time-series representation learning is a fundamental task for time-series analysis. While significant progress has been made to achieve accurate representations for downstream appl…
A General Taylor Framework for Unifying and Revisiting Attribution Methods
Huiqi Deng, Na Zou, Mengnan Du +3
Attribution methods provide an insight into the decision-making process of machine learning models, especially deep neural networks, by assigning contribution scores to each indivi…
Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution
Huiqi Deng, Na Zou, Weifu Chen +3
Back propagation based visualizations have been proposed to interpret deep neural networks (DNNs), some of which produce interpretations with good visual quality. However, there ex…
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models
Mengnan Du, Varun Manjunatha, Rajiv Jain +5
Recent studies indicate that NLU models are prone to rely on shortcut features for prediction, without achieving true language understanding. As a result, these models fail to gene…
Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation
Fan Yang, Ninghao Liu, Mengnan Du +1
With the wide use of deep neural networks (DNN), model interpretability has become a critical concern, since explainable decisions are preferred in high-stake scenarios. Current in…