Mengnan Du

208 papers A* 32A 10B 5C 2Journal 130Unranked 29
YearRankTypeTitle / Venue / Authors
2026 J jnl
AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling.
CoRR
Yongliang Miao, Yangyang Liang, Mengnan Du
2026 — conf
DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router.
EACL (Findings)
Minghao Guo, Qingcheng Zeng, Xujiang Zhao, Yanchi Liu, Wenchao Yu, Mengnan Du, Haifeng Chen, Wei Cheng
2026 — conf
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering.
EACL (Findings)
Haiyan Zhao, Xuansheng Wu, Fan Yang, Bo Shen, Ninghao Liu, Mengnan Du
2026 — conf
FaithLM: Towards Faithful Explanations for Large Language Models.
EACL (Volume 1: Long Papers)
Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang, Shaochen Zhong, Fan Yang, Andrew Wen, Mengnan Du, Xuanting Cai, Vladimir Braverman, Xia Hu
2026 J jnl
Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs.
CoRR
Mingyu Jin, Yutong Yin, Jingcheng Niu, Qingcheng Zeng, Wujiang Xu, Mengnan Du, Wei Cheng, Zhaoran Wang, Tianlong Chen, Dimitris N. Metaxas
2026 J jnl
FinAnchor: Aligned Multi-Model Representations for Financial Prediction.
CoRR
Zirui He, Huopu Zhang, Yanguang Liu, Sirui Wu, Mengnan Du
2026 A* conf
Fine-Grained Interpretation of Political Opinions in Large Language Models.
AAAI
Jingyu Hu, Mengyue Yang, Mengnan Du, Weiru Liu
2026 A* conf
KnowThyself: An Agentic Assistant for LLM Interpretability.
AAAI
Suraj Prasai, Mengnan Du, Ying Zhang, Fan Yang
2026 J jnl
LLM Agents in Law: Taxonomy, Applications, and Challenges.
CoRR
Shuang Liu, Ruijia Zhang, Ruoyun Ma, Yujia Deng, Lanyi Zhu, Jiayu Li, Zelong Li, Zhibin Shen, Mengnan Du
2026 J jnl
NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models.
CoRR
Weiqi Liu, Yongliang Miao, Haiyan Zhao, Yanguang Liu, Mengnan Du
2026 — conf
SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models.
EACL (Industry Track)
Jiaojiao Han, Wujiang Xu, Mingyu Jin, Mengnan Du
2025 J jnl
A Comprehensive Survey of Synthetic Tabular Data Generation.
CoRR
Ruxue Shi, Yili Wang, Mengnan Du, Xu Shen, Xin Wang
2025 — conf
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models.
EMNLP (Findings)
Dong Shu, Xuansheng Wu, Haiyan Zhao, Daking Rai, Ziyu Yao, Ninghao Liu, Mengnan Du
2025 J jnl
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models.
CoRR
Dong Shu, Xuansheng Wu, Haiyan Zhao, Daking Rai, Ziyu Yao, Ninghao Liu, Mengnan Du
2025 J jnl
AdaptiveK Sparse Autoencoders: Dynamic Sparsity Allocation for Interpretable LLM Representations.
CoRR
Yifei Yao, Mengnan Du
2025 J jnl
Aligning large language models and geometric deep models for protein representation.
Patterns
Dong Shu, Bingbing Duan, Kai Guo, Kaixiong Zhou, Jiliang Tang, Mengnan Du
2025 J jnl
Attribution Explanations for Deep Neural Networks: A Theoretical Perspective.
CoRR
Huiqi Deng, Hongbin Pei, Quanshi Zhang, Mengnan Du
2025 J jnl
BATED: Learning fair representation for Pre-trained Language Models via biased teacher-guided disentanglement.
Artif. Intell.
Yingji Li, Mengnan Du, Rui Song, Mu Liu, Ying Wang
2025 A* conf
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders.
EMNLP
Dong Shu, Xuansheng Wu, Haiyan Zhao, Mengnan Du, Ninghao Liu
2025 J jnl
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders.
CoRR
Dong Shu, Xuansheng Wu, Haiyan Zhao, Mengnan Du, Ninghao Liu
2025 A* conf
Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution.
ICLR
Haiyan Zhao, Heng Zhao, Bo Shen, Ali Payani, Fan Yang, Mengnan Du
2025 J jnl
Boosting Fair Classifier Generalization through Adaptive Priority Reweighing.
ACM Trans. Knowl. Discov. Data
Zhihao Hu, Yiran Xu, Mengnan Du, Jindong Gu, Xinmei Tian, Fengxiang He
2025 A* conf
Comparative Analysis of Demonstration Selection Algorithms for In-Context Learning in Large Language Models (Student Abstract).
AAAI
Dong Shu, Mengnan Du
2025 A* conf
Concept-Centric Token Interpretation for Vector-Quantized Generative Models.
ICML
Tianze Yang, Yucheng Shi, Mengnan Du, Xuansheng Wu, Qiaoyu Tan, Jin Sun, Ninghao Liu
2025 J jnl
Concept-Centric Token Interpretation for Vector-Quantized Generative Models.
CoRR
Tianze Yang, Yucheng Shi, Mengnan Du, Xuansheng Wu, Qiaoyu Tan, Jin Sun, Ninghao Liu
2025 J jnl
ContractEval: Benchmarking LLMs for Clause-Level Legal Risk Identification in Commercial Contracts.
CoRR
Shuang Liu, Zelong Li, Ruoyun Ma, Haiyan Zhao, Mengnan Du
2025 J jnl
Counterfactual Visual Explanation via Causally-Guided Adversarial Steering.
CoRR
Yiran Qiao, Disheng Liu, Yiren Lu, Yu Yin, Mengnan Du, Jing Ma
2025 J jnl
DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models.
CoRR
Zihao Li, Ruixiang Tang, Lu Cheng, Shuaiqiang Wang, Dawei Yin, Mengnan Du
2025 J jnl
DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models.
SIGKDD Explor.
Zihao Li, Ruixiang Tang, Lu Cheng, Shuaiqiang Wang, Dawei Yin, Mengnan Du
2025 — conf
Data-centric NLP Backdoor Defense from the Lens of Memorization.
NAACL (Findings)
Zhenting Wang, Zhizhi Wang, Mingyu Jin, Mengnan Du, Juan Zhai, Shiqing Ma
2025 J jnl
DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router.
CoRR
Minghao Guo, Qingcheng Zeng, Xujiang Zhao, Yanchi Liu, Wenchao Yu, Mengnan Du, Haifeng Chen, Wei Cheng
2025 B conf
DemoShapley: Valuation of Demonstrations for In-Context Learning.
IEEE Big Data
Shan Xie, Man Luo, Chadly Daniel Stern, Mengnan Du, Lu Cheng
2025 J jnl
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering.
CoRR
Haiyan Zhao, Xuansheng Wu, Fan Yang, Bo Shen, Ninghao Liu, Mengnan Du
2025 B conf
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
COLING
Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
2025 J jnl
Fair Machine Learning in Healthcare: A Survey.
IEEE Trans. Artif. Intell.
Qizhang Feng, Mengnan Du, Na Zou, Xia Ben Hu
2025 J jnl
Fair-RGNN: Mitigating Relational Bias on Knowledge Graphs.
ACM Trans. Knowl. Discov. Data
Yu-Neng Chuang, Kwei-Herng Lai, Ruixiang Tang, Mengnan Du, Chia-Yuan Chang, Na Zou, Xia Hu
2025 A* conf
Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models.
EMNLP
Zihao Li, Xu Wang, Yuzhe Yang, Ziyu Yao, Haoyi Xiong, Mengnan Du
2025 J jnl
Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models.
CoRR
Zihao Li, Xu Wang, Yuzhe Yang, Ziyu Yao, Haoyi Xiong, Mengnan Du
2025 J jnl
FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction.
CoRR
Dong Shu, Yanguang Liu, Huopu Zhang, Mengnan Du
2025 J jnl
FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models.
CoRR
Dong Shu, Haoyang Yuan, Yuchen Wang, Yanguang Liu, Huopu Zhang, Haiyan Zhao, Mengnan Du
2025 J jnl
Fine-Grained Interpretation of Political Opinions in Large Language Models.
CoRR
Jingyu Hu, Mengyue Yang, Mengnan Du, Weiru Liu
2025 A* conf
From Commands to Prompts: LLM-based Semantic File System for AIOS.
ICLR
Zeru Shi, Kai Mei, Mingyu Jin, Yongye Su, Chaoji Zuo, Wenyue Hua, Wujiang Xu, Yujie Ren, Zirui Liu, Mengnan Du, Dong Deng, Yongfeng Zhang
2025 — conf
Improving LLM Reasoning through Interpretable Role-Playing Steering.
EMNLP (Findings)
Anyi Wang, Dong Shu, Yifan Wang, Yunpu Ma, Mengnan Du
2025 J jnl
Improving LLM Reasoning through Interpretable Role-Playing Steering.
CoRR
Anyi Wang, Dong Shu, Yifan Wang, Yunpu Ma, Mengnan Du
2025 A* conf
Invisible Backdoor Attack against Self-supervised Learning.
CVPR
Hanrong Zhang, Zhenting Wang, Boheng Li, Fulin Lin, Tingxu Han, Mingyu Jin, Chenlu Zhan, Mengnan Du, Hongwei Wang, Shiqing Ma
2025 J jnl
KnowThyself: An Agentic Assistant for LLM Interpretability.
CoRR
Suraj Prasai, Mengnan Du, Ying Zhang, Fan Yang
2025 A* conf
Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages.
AAAI
Zihao Li, Yucheng Shi, Zirui Liu, Fan Yang, Ali Payani, Ninghao Liu, Mengnan Du
2025 — conf
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability.
EMNLP (Findings)
Dong Shu, Haiyan Zhao, Jingyu Hu, Weiru Liu, Ali Payani, Lu Cheng, Mengnan Du
2025 J jnl
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability.
CoRR
Dong Shu, Haiyan Zhao, Jingyu Hu, Weiru Liu, Lu Cheng, Mengnan Du
2025 A* conf
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding.
ICML
Mingyu Jin, Kai Mei, Wujiang Xu, Mingjie Sun, Ruixiang Tang, Mengnan Du, Zirui Liu, Yongfeng Zhang
2025 J jnl
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding.
CoRR
Mingyu Jin, Kai Mei, Wujiang Xu, Mingjie Sun, Ruixiang Tang, Mengnan Du, Zirui Liu, Yongfeng Zhang
2025 J jnl
MemLens: Uncovering Memorization in LLMs with Activation Trajectories.
CoRR
Zirui He, Haiyan Zhao, Ali Payani, Mengnan Du
2025 — conf
NPC-TAG: Node Prompts for Classification on Text Attributed Graphs with LLMs.
ICDM (Workshops)
Uras Varolgunes, Mengnan Du, Dantong Yu
2025 — conf
Physics-Informed Attention-Enhanced Fourier Neural Operator for Solar Magnetic Field Extrapolations.
ICDM (Workshops)
Jinghao Cao, Qi Li, Mengnan Du, Haimin Wang, Bo Shen
2025 J jnl
Physics-informed Attention-enhanced Fourier Neural Operator for Solar Magnetic Field Extrapolations.
CoRR
Jinghao Cao, Qin Li, Mengnan Du, Haimin Wang, Bo Shen
2025 J jnl
Rep2Text: Decoding Full Text from a Single LLM Token Representation.
CoRR
Haiyan Zhao, Zirui He, Fan Yang, Ali Payani, Mengnan Du
2025 J jnl
SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection.
CoRR
Huopu Zhang, Yanguang Liu, Mengnan Du
2025 A* conf
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models.
EMNLP
Zirui He, Mingyu Jin, Bo Shen, Ali Payani, Yongfeng Zhang, Mengnan Du
2025 J jnl
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models.
CoRR
Zirui He, Mingyu Jin, Bo Shen, Ali Payani, Yongfeng Zhang, Mengnan Du
2025 J jnl
SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models.
CoRR
Jiaojiao Han, Wujiang Xu, Mingyu Jin, Mengnan Du
2025 J jnl
SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models.
CoRR
Zirui He, Haiyan Zhao, Yiran Qiao, Fan Yang, Ali Payani, Jing Ma, Mengnan Du
2025 J jnl
Towards Uncovering How Large Language ModelsWork: An Interpretability Perspective.
SIGKDD Explor.
Haiyan Zhao, Fan Yang, Bo Shen, Ali Payani, Himabindu Lakkaraju, Mengnan Du
2024 — conf
AI Driven Online Advertising: Market Design, Generative AI, and Ethics.
WWW (Companion Volume)
Fengxiang He, Mengnan Du, Aris Filos-Ratsikas, Lu Cheng, Qingquan Song, Min Lin, John Vines
2024 J jnl
Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution.
CoRR
Haiyan Zhao, Heng Zhao, Bo Shen, Ali Payani, Fan Yang, Mengnan Du
2024 J jnl
Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning.
CoRR
Dong Shu, Mengnan Du
2024 — conf
Data-Centric Explainable Debiasing for Improving Fairness in Pre-trained Language Models.
ACL (Findings)
Yingji Li, Mengnan Du, Rui Song, Xin Wang, Ying Wang
2024 J jnl
Data-centric NLP Backdoor Defense from the Lens of Memorization.
CoRR
Zhenting Wang, Zhizhi Wang, Mingyu Jin, Mengnan Du, Juan Zhai, Shiqing Ma
2024 C conf
DataFrame QA: A Universal LLM Framework on DataFrame Question Answering Without Data Exposure.
ACML
Junyi Ye, Mengnan Du, Guiling Wang
2024 J jnl
DataFrame QA: A Universal LLM Framework on DataFrame Question Answering Without Data Exposure.
CoRR
Junyi Ye, Mengnan Du, Guiling Wang
2024 B conf
Deep Computer Vision for Solar Physics Big Data: Opportunities and Challenges [Vision Paper].
IEEE Big Data
Bo Shen, Marco Marena, Chenyang Li, Qin Li, Haodi Jiang, Mengnan Du, Jiajun Xu, Haimin Wang
2024 J jnl
Deep Computer Vision for Solar Physics Big Data: Opportunities and Challenges.
CoRR
Bo Shen, Marco Marena, Chenyang Li, Qin Li, Haodi Jiang, Mengnan Du, Jiajun Xu, Haimin Wang
2024 J jnl
DemoShapley: Valuation of Demonstrations for In-Context Learning.
CoRR
Shan Xie, Man Luo, Chadly Daniel Stern, Mengnan Du, Lu Cheng
2024 — conf
Enhancing Fairness in In-Context Learning: Prioritizing Minority Samples in Demonstrations.
Tiny Papers @ ICLR
Jingyu Hu, Mengnan Du
2024 J jnl
Explainability for Large Language Models: A Survey.
ACM Trans. Intell. Syst. Technol.
Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du
2024 A* conf
Explaining Time Series via Contrastive and Locally Sparse Perturbations.
ICLR
Zichuan Liu, Yingying Zhang, Tianchun Wang, Zefan Wang, Dongsheng Luo, Mengnan Du, Min Wu, Yi Wang, Chunlin Chen, Lunting Fan, Qingsong Wen
2024 J jnl
Explaining Time Series via Contrastive and Locally Sparse Perturbations.
CoRR
Zichuan Liu, Yingying Zhang, Tianchun Wang, Zefan Wang, Dongsheng Luo, Mengnan Du, Min Wu, Yi Wang, Chunlin Chen, Lunting Fan, Qingsong Wen
2024 J jnl
Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training.
CoRR
Jiamin Chen, Xuhong Li, Yanwu Xu, Mengnan Du, Haoyi Xiong
2024 J jnl
Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?
CoRR
Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
2024 J jnl
Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis.
CoRR
Daoyang Li, Mingyu Jin, Qingcheng Zeng, Haiyan Zhao, Mengnan Du
2024 J jnl
Exploring the Alignment Landscape: LLMs and Geometric Deep Models in Protein Representation.
CoRR
Dong Shu, Bingbing Duan, Kai Guo, Kaixiong Zhou, Jiliang Tang, Mengnan Du
2024 J jnl
From Commands to Prompts: LLM-based Semantic File System for AIOS.
CoRR
Zeru Shi, Kai Mei, Mingyu Jin, Yongye Su, Chaoji Zuo, Wenyue Hua, Wujiang Xu, Yujie Ren, Zirui Liu, Mengnan Du, Dong Deng, Yongfeng Zhang
2024 B conf
Global-local Fourier Neural Operator for Accelerating Coronal Magnetic Field Model.
IEEE Big Data
Yutao Du, Qin Li, Raghav Gnanasambandam, Mengnan Du, Haimin Wang, Bo Shen
2024 J jnl
Health-LLM: Personalized Retrieval-Augmented Disease Prediction System.
CoRR
Mingyu Jin, Qinkai Yu, Dong Shu, Chong Zhang, Lizhou Fan, Wenyue Hua, Suiyuan Zhu, Yanda Meng, Zhenting Wang, Mengnan Du, Yongfeng Zhang
2024 C conf
Knowledge Graph Large Language Model (KG-LLM) for Link Prediction.
ACML
Dong Shu, Tianle Chen, Mingyu Jin, Chong Zhang, Mengnan Du, Yongfeng Zhang
2024 J jnl
Knowledge Graph Large Language Model (KG-LLM) for Link Prediction.
CoRR
Dong Shu, Tianle Chen, Mingyu Jin, Yiting Zhang, Chong Zhang, Mengnan Du, Yongfeng Zhang
2024 J jnl
Large Language Models As Faithful Explainers.
CoRR
Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang, Fan Yang, Mengnan Du, Xuanting Cai, Xia Hu
2024 A conf
LawLLM: Law Large Language Model for the US Legal System.
CIKM
Dong Shu, Haoran Zhao, Xukun Liu, David Demeter, Mengnan Du, Yongfeng Zhang
2024 J jnl
LawLLM: Law Large Language Model for the US Legal System.
CoRR
Dong Shu, Haoran Zhao, Xukun Liu, David Demeter, Mengnan Du, Yongfeng Zhang
2024 — conf
Mitigating Shortcuts in Language Models with Soft Label Encoding.
LREC/COLING
Zirui He, Huiqi Deng, Haiyan Zhao, Ninghao Liu, Mengnan Du
2024 J jnl
Mitigating social biases of pre-trained language models via contrastive self-debiasing with double data augmentation.
Artif. Intell.
Yingji Li, Mengnan Du, Rui Song, Xin Wang, Mingchen Sun, Ying Wang
2024 J jnl
Neural Operator for Accelerating Coronal Magnetic Field Model.
CoRR
Yutao Du, Qin Li, Raghav Gnanasambandam, Mengnan Du, Haimin Wang, Bo Shen
2024 J jnl
Opening the Black Box of Large Language Models: Two Views on Holistic Interpretability.
CoRR
Haiyan Zhao, Fan Yang, Himabindu Lakkaraju, Mengnan Du
2024 J jnl
ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction.
CoRR
Mingyu Jin, Haochen Xue, Zhenting Wang, Boming Kang, Ruosong Ye, Kaixiong Zhou, Mengnan Du, Yongfeng Zhang
2024 — conf
ProxiMix: Enhancing Fairness with Proximity Samples in Subgroups.
AEQUITAS@ECAI
Jingyu Hu, Jun Hong, Mengnan Du, Weiru Liu
2024 J jnl
ProxiMix: Enhancing Fairness with Proximity Samples in Subgroups.
CoRR
Jingyu Hu, Jun Hong, Mengnan Du, Weiru Liu
2024 J jnl
Quantifying Multilingual Performance of Large Language Models Across Languages.
CoRR
Zihao Li, Yucheng Shi, Zirui Liu, Fan Yang, Ninghao Liu, Mengnan Du
2024 — conf
Secure Your Model: An Effective Key Prompt Protection Mechanism for Large Language Models.
NAACL-HLT (Findings)
Ruixiang Tang, Yu-Neng Chuang, Xuanting Cai, Mengnan Du, Xia Hu
2024 J jnl
Shortcut Learning of Large Language Models in Natural Language Understanding.
Commun. ACM
Mengnan Du, Fengxiang He, Na Zou, Dacheng Tao, Xia Hu
2024 A* conf
Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning.
EMNLP
Jingyu Hu, Weiru Liu, Mengnan Du
2024 J jnl
Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning.
CoRR
Jingyu Hu, Weiru Liu, Mengnan Du
2024 A* conf
TVE: Learning Meta-attribution for Transferable Vision Explainer.
ICML
Guanchu Wang, Yu-Neng Chuang, Fan Yang, Mengnan Du, Chia-Yuan Chang, Shaochen Zhong, Zirui Liu, Zhaozhuo Xu, Kaixiong Zhou, Xuanting Cai, Xia Hu
2024 — conf
The Impact of Reasoning Step Length on Large Language Models.
ACL (Findings)
Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, Mengnan Du
2024 J jnl
The Impact of Reasoning Step Length on Large Language Models.
CoRR
Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, Mengnan Du
2024 J jnl
Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities.
CoRR
Mingyu Jin, Hua Tang, Chong Zhang, Qinkai Yu, Chengzhi Liu, Suiyuan Zhu, Yongfeng Zhang, Mengnan Du
2024 J jnl
Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities.
SIGKDD Explor.
Hua Tang, Chong Zhang, Mingyu Jin, Qinkai Yu, Zhenting Wang, Xiaobo Jin, Yongfeng Zhang, Mengnan Du
2024 J jnl
Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective.
CoRR
Haoyi Xiong, Xuhong Li, Xiaofei Zhang, Jiamin Chen, Xinhao Sun, Yuchen Li, Zeyi Sun, Mengnan Du
2024 J jnl
Towards Imperceptible Backdoor Attack in Self-supervised Learning.
CoRR
Hanrong Zhang, Zhenting Wang, Tingxu Han, Mingyu Jin, Chenlu Zhan, Mengnan Du, Hongwei Wang, Shiqing Ma
2024 J jnl
Unifying Fourteen Post-Hoc Attribution Methods With Taylor Interactions.
IEEE Trans. Pattern Anal. Mach. Intell.
Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Ziwei Yang, Zheyang Li, Quanshi Zhang
2024 — conf
Unveiling Project-Specific Bias in Neural Code Models.
LREC/COLING
Zhiming Li, Yanzhou Li, Tianlin Li, Mengnan Du, Bozhi Wu, Yushi Cao, Junzhe Jiang, Yang Liu
2024 J jnl
Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era.
CoRR
Xuansheng Wu, Haiyan Zhao, Yaochen Zhu, Yucheng Shi, Fan Yang, Tianming Liu, Xiaoming Zhai, Wenlin Yao, Jundong Li, Mengnan Du, Ninghao Liu
2024 J jnl
What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents.
CoRR
Mingyu Jin, Beichen Wang, Zhaoqian Xue, Suiyuan Zhu, Wenyue Hua, Hua Tang, Kai Mei, Mengnan Du, Yongfeng Zhang
2024 J jnl
When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments.
CoRR
Chong Zhang, Xinyi Liu, Mingyu Jin, Zhongmou Zhang, Lingyao Li, Zhenting Wang, Wenyue Hua, Dong Shu, Suiyuan Zhu, Xiaobo Jin, Sujian Li, Mengnan Du, Yongfeng Zhang
2024 J jnl
When Search Engine Services Meet Large Language Models: Visions and Challenges.
IEEE Trans. Serv. Comput.
Haoyi Xiong, Jiang Bian, Yuchen Li, Xuhong Li, Mengnan Du, Shuaiqiang Wang, Dawei Yin, Sumi Helal
2024 J jnl
When Search Engine Services meet Large Language Models: Visions and Challenges.
CoRR
Haoyi Xiong, Jiang Bian, Yuchen Li, Xuhong Li, Mengnan Du, Shuaiqiang Wang, Dawei Yin, Sumi Helal
2023 J jnl
A Survey on Fairness in Large Language Models.
CoRR
Yingji Li, Mengnan Du, Rui Song, Xin Wang, Ying Wang
2023 J jnl
A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier.
CoRR
Hua Tang, Lu Cheng, Ninghao Liu, Mengnan Du
2023 A conf
Attacking Neural Networks with Neural Networks: Towards Deep Synchronization for Backdoor Attacks.
CIKM
Zihan Guan, Lichao Sun, Mengnan Du, Ninghao Liu
2023 A* conf
Black-box Backdoor Defense via Zero-shot Image Purification.
NeurIPS
Yucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Jin Sun, Ninghao Liu
2023 J jnl
Black-box Backdoor Defense via Zero-shot Image Purification.
CoRR
Yucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Ninghao Liu
2023 J jnl
Boosting Fair Classifier Generalization through Adaptive Priority Reweighing.
CoRR
Zhihao Hu, Yiran Xu, Mengnan Du, Jindong Gu, Xinmei Tian, Fengxiang He
2023 J jnl
DEGREE: Decomposition Based Explanation For Graph Neural Networks.
CoRR
Qizhang Feng, Ninghao Liu, Fan Yang, Ruixiang Tang, Mengnan Du, Xia Hu
2023 J jnl
DISPEL: Domain Generalization via Domain-Specific Liberating.
CoRR
Chia-Yuan Chang, Yu-Neng Chuang, Guanchu Wang, Mengnan Du, Zou Na
2023 — conf
Deep Serial Number: Computational Watermark for DNN Intellectual Property Protection.
ECML/PKDD (6)
Ruixiang Tang, Mengnan Du, Xia Hu
2023 J jnl
Efficient XAI Techniques: A Taxonomic Survey.
CoRR
Yu-Neng Chuang, Guanchu Wang, Fan Yang, Zirui Liu, Xuanting Cai, Mengnan Du, Xia Ben Hu
2023 — conf
Error Detection on Knowledge Graphs with Triple Embedding.
EUSIPCO
Yezi Liu, Qinggang Zhang, Mengnan Du, Xiao Huang, Xia Hu
2023 J jnl
Explainability for Large Language Models: A Survey.
CoRR
Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du
2023 A conf
Exposing Model Theft: A Robust and Transferable Watermark for Thwarting Model Extraction Attacks.
CIKM
Ruixiang Tang, Hongye Jin, Mengnan Du, Curtis Wigington, Rajiv Jain, Xia Hu
2023 A* conf
FAIRER: Fairness as Decision Rationale Alignment.
ICML
Tianlin Li, Qing Guo, Aishan Liu, Mengnan Du, Zhiming Li, Yang Liu
2023 J jnl
FAIRER: Fairness as Decision Rationale Alignment.
CoRR
Tianlin Li, Qing Guo, Aishan Liu, Mengnan Du, Zhiming Li, Yang Liu
2023 A* conf
Fairness via Group Contribution Matching.
IJCAI
Tianlin Li, Zhiming Li, Anran Li, Mengnan Du, Aishan Liu, Qing Guo, Guozhu Meng, Yang Liu
2023 J jnl
LETA: Learning Transferable Attribution for Generic Vision Explainer.
CoRR
Guanchu Wang, Yu-Neng Chuang, Fan Yang, Mengnan Du, Chia-Yuan Chang, Shaochen Zhong, Zirui Liu, Zhaozhuo Xu, Kaixiong Zhou, Xuanting Cai, Xia Hu
2023 A* conf
M
NeurIPS
Xuhong Li, Mengnan Du, Jiamin Chen, Yekun Chai, Himabindu Lakkaraju, Haoyi Xiong
2023 — conf
Mitigating Algorithmic Bias with Limited Annotations.
ECML/PKDD (2)
Guanchu Wang, Mengnan Du, Ninghao Liu, Na Zou, Xia Ben Hu
2023 J jnl
Mitigating Shortcuts in Language Models with Soft Label Encoding.
CoRR
Zirui He, Huiqi Deng, Haiyan Zhao, Ninghao Liu, Mengnan Du
2023 — conf
Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases.
ACL (1)
Yingji Li, Mengnan Du, Xin Wang, Ying Wang
2023 J jnl
Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases.
CoRR
Yingji Li, Mengnan Du, Xin Wang, Ying Wang
2023 — conf
Proportionate Diversification of Top-k LLM Results using Database Queries.
VLDB Workshops
Thinh On, Subhodeep Ghosh, Mengnan Du, Senjuti Basu Roy
2023 A conf
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding.
EACL
Mengnan Du, Subhabrata Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Hassan Awadallah
2023 J jnl
Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions.
CoRR
Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Ziwei Yang, Zheyang Li, Quanshi Zhang
2023 A conf
XGBD: Explanation-Guided Graph Backdoor Detection.
ECAI
Zihan Guan, Mengnan Du, Ninghao Liu
2023 J jnl
XGBD: Explanation-Guided Graph Backdoor Detection.
CoRR
Zihan Guan, Mengnan Du, Ninghao Liu
2022 A* conf
Accelerating Shapley Explanation via Contributive Cooperator Selection.
ICML
Guanchu Wang, Yu-Neng Chuang, Mengnan Du, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai, Xia Ben Hu
2022 J jnl
Accelerating Shapley Explanation via Contributive Cooperator Selection.
CoRR
Guanchu Wang, Yu-Neng Chuang, Mengnan Du, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai, Xia Ben Hu
2022 A* conf
DEGREE: Decomposition Based Explanation for Graph Neural Networks.
ICLR
Qizhang Feng, Ninghao Liu, Fan Yang, Ruixiang Tang, Mengnan Du, Xia Hu
2022 J jnl
Differentiated Explanation of Deep Neural Networks With Skewed Distributions.
IEEE Trans. Pattern Anal. Mach. Intell.
Weijie Fu, Meng Wang, Mengnan Du, Ninghao Liu, Shijie Hao, Xia Hu
2022 J jnl
Fair Machine Learning in Healthcare: A Review.
CoRR
Qizhang Feng, Mengnan Du, Na Zou, Xia Hu
2022 J jnl
Mitigating Algorithmic Bias with Limited Annotations.
CoRR
Guanchu Wang, Mengnan Du, Ninghao Liu, Na Zou, Xia Ben Hu
2022 J jnl
Mitigating Relational Bias on Knowledge Graphs.
CoRR
Yu-Neng Chuang, Kwei-Herng Lai, Ruixiang Tang, Mengnan Du, Chia-Yuan Chang, Na Zou, Xia Hu
2022 J jnl
Shortcut Learning of Large Language Models in Natural Language Understanding: A Survey.
CoRR
Mengnan Du, Fengxiang He, Na Zou, Dacheng Tao, Xia Hu
2022 J jnl
Subarchitecture Ensemble Pruning in Neural Architecture Search.
IEEE Trans. Neural Networks Learn. Syst.
Yijun Bian, Qingquan Song, Mengnan Du, Jun Yao, Huanhuan Chen, Xia Hu
2022 A* conf
Towards Debiasing DNN Models from Spurious Feature Influence.
AAAI
Mengnan Du, Ruixiang Tang, Weijie Fu, Xia Hu
2022 A* conf
Towards Learning Disentangled Representations for Time Series.
KDD
Yuening Li, Zhengzhang Chen, Daochen Zha, Mengnan Du, Jingchao Ni, Denghui Zhang, Haifeng Chen, Xia Hu
2022 J jnl
Understanding Social Biases Behind Location Names in Contextual Word Embedding Models.
IEEE Trans. Comput. Soc. Syst.
Fangsheng Wu, Mengnan Du, Chao Fan, Ruixiang Tang, Yang Yang, Ali Mostafavi, Xia Hu
2022 J jnl
Unveiling Project-Specific Bias in Neural Code Models.
CoRR
Zhiming Li, Yanzhou Li, Tianlin Li, Mengnan Du, Bozhi Wu, Yushi Cao, Xiaofei Xie, Yi Li, Yang Liu
2021 A* conf
A Unified Taylor Framework for Revisiting Attribution Methods.
AAAI
Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Xia Hu
2021 J jnl
Adversarial Attacks and Defenses: An Interpretation Perspective.
SIGKDD Explor.
Ninghao Liu, Mengnan Du, Ruocheng Guo, Huan Liu, Xia Hu
2021 J jnl
Fairness in Deep Learning: A Computational Perspective.
IEEE Intell. Syst.
Mengnan Du, Fan Yang, Na Zou, Xia Hu
2021 A* conf
Fairness via Representation Neutralization.
NeurIPS
Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, Xia Ben Hu
2021 J jnl
Fairness via Representation Neutralization.
CoRR
Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, Xia Ben Hu
2021 J jnl
Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation.
CoRR
Fan Yang, Ninghao Liu, Mengnan Du, Xia Hu
2021 J jnl
Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation.
SIGKDD Explor.
Fan Yang, Ninghao Liu, Mengnan Du, Xia Hu
2021 J jnl
Learning Disentangled Representations for Time Series.
CoRR
Yuening Li, Zhengzhang Chen, Daochen Zha, Mengnan Du, Denghui Zhang, Haifeng Chen, Xia Hu
2021 J jnl
Learning credible DNNs via incorporating prior knowledge and model local explanation.
Knowl. Inf. Syst.
Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu
2021 A conf
Machine Learning Explanations to Prevent Overtrust in Fake News Detection.
ICWSM
Sina Mohseni, Fan Yang, Shiva K. Pentyala, Mengnan Du, Yi Liu, Nic Lupfer, Xia Hu, Shuiwang Ji, Eric D. Ragan
2021 A* conf
Mitigating Gender Bias in Captioning Systems.
WWW
Ruixiang Tang, Mengnan Du, Yuening Li, Zirui Liu, Na Zou, Xia Hu
2021 — conf
MultiCode: A Unified Code Analysis Framework based on Multi-type and Multi-granularity Semantic Learning.
ISSRE Workshops
Xu Duan, Jingzheng Wu, Mengnan Du, Tianyue Luo, Mutian Yang, Yanjun Wu
2021 A* conf
Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution.
KDD
Huiqi Deng, Na Zou, Weifu Chen, Guocan Feng, Mengnan Du, Xia Hu
2021 J jnl
Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution.
CoRR
Huiqi Deng, Na Zou, Weifu Chen, Guocan Feng, Mengnan Du, Xia Hu
2021 — conf
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models.
NAACL-HLT
Mengnan Du, Varun Manjunatha, Rajiv Jain, Ruchi Deshpande, Franck Dernoncourt, Jiuxiang Gu, Tong Sun, Xia Hu
2021 J jnl
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models.
CoRR
Mengnan Du, Varun Manjunatha, Rajiv Jain, Ruchi Deshpande, Franck Dernoncourt, Jiuxiang Gu, Tong Sun, Xia Hu
2021 J jnl
What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression.
CoRR
Mengnan Du, Subhabrata Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Hassan Awadallah
2020 J jnl
A Unified Taylor Framework for Revisiting Attribution Methods.
CoRR
Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Xia Hu
2020 J jnl
A deep learning approach for identifying cancer survivors living with post-traumatic stress disorder on Twitter.
BMC Medical Informatics Decis. Mak.
Nur Hafieza Ismail, Ninghao Liu, Mengnan Du, Zhe He, Xia Hu
2020 J jnl
Adversarial Machine Learning: An Interpretation Perspective.
CoRR
Ninghao Liu, Mengnan Du, Xia Hu
2020 A* conf
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks.
KDD
Ruixiang Tang, Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu
2020 J jnl
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks.
CoRR
Ruixiang Tang, Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu
2020 A conf
Deep Neural Networks with Knowledge Instillation.
SDM
Fan Yang, Ninghao Liu, Mengnan Du, Kaixiong Zhou, Shuiwang Ji, Xia Hu
2020 J jnl
Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection.
CoRR
Ruixiang Tang, Mengnan Du, Xia Hu
2020 J jnl
Machine Learning Explanations to Prevent Overtrust in Fake News Detection.
CoRR
Sina Mohseni, Fan Yang, Shiva K. Pentyala, Mengnan Du, Yi Liu, Nic Lupfer, Xia Hu, Shuiwang Ji, Eric D. Ragan
2020 J jnl
Mitigating Gender Bias in Captioning Systems.
CoRR
Ruixiang Tang, Mengnan Du, Yuening Li, Zirui Liu, Xia Hu
2020 — conf
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks.
CVPR Workshops
Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel, Xia Hu
2020 J jnl
Techniques for interpretable machine learning.
Commun. ACM
Mengnan Du, Ninghao Liu, Xia Hu
2020 A conf
Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder.
CIKM
Mengnan Du, Shiva K. Pentyala, Yuening Li, Xia Hu
2019 B conf
Deep Structured Cross-Modal Anomaly Detection.
IJCNN
Yuening Li, Ninghao Liu, Jundong Li, Mengnan Du, Xia Hu
2019 J jnl
Deep Structured Cross-Modal Anomaly Detection.
CoRR
Yuening Li, Ninghao Liu, Jundong Li, Mengnan Du, Xia Hu
2019 J jnl
Evaluating Explanation Without Ground Truth in Interpretable Machine Learning.
CoRR
Fan Yang, Mengnan Du, Xia Hu
2019 J jnl
Fairness in Deep Learning: A Computational Perspective.
CoRR
Mengnan Du, Fan Yang, Na Zou, Xia Hu
2019 — conf
Identification of Cancer Survivors Living with PTSD on Social Media.
MedInfo
Nur Hafieza Ismail, Ninghao Liu, Mengnan Du, Zhe He, Xia Hu
2019 A* conf
Learning Credible Deep Neural Networks with Rationale Regularization.
ICDM
Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu
2019 J jnl
Learning Credible Deep Neural Networks with Rationale Regularization.
CoRR
Mengnan Du, Ninghao Liu, Fan Yang, Xia Hu
2019 — conf
Multivariate Multi-step Deep Learning Time Series Approach in Forecasting Parkinson's Disease Future Severity Progression.
BCB
Nur Hafieza Ismail, Mengnan Du, Diego Martinez, Zhe He
2019 A* conf
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition.
WWW
Mengnan Du, Ninghao Liu, Fan Yang, Shuiwang Ji, Xia Hu
2019 J jnl
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition.
CoRR
Mengnan Du, Ninghao Liu, Fan Yang, Shuiwang Ji, Xia Hu
2019 A conf
Representation Interpretation with Spatial Encoding and Multimodal Analytics.
WSDM
Ninghao Liu, Mengnan Du, Xia Hu
2019 J jnl
Score-CAM: Improved Visual Explanations Via Score-Weighted Class Activation Mapping.
CoRR
Haofan Wang, Mengnan Du, Fan Yang, Zijian Zhang
2019 A conf
SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks.
CIKM
Yuening Li, Xiao Huang, Jundong Li, Mengnan Du, Na Zou
2019 J jnl
SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks.
CoRR
Yuening Li, Xiao Huang, Jundong Li, Mengnan Du, Na Zou
2019 J jnl
Sub-Architecture Ensemble Pruning in Neural Architecture Search.
CoRR
Yijun Bian, Qingquan Song, Mengnan Du, Jun Yao, Huanhuan Chen, Xia Hu
2019 J jnl
Towards Generalizable Forgery Detection with Locality-aware AutoEncoder.
CoRR
Mengnan Du, Shiva K. Pentyala, Yuening Li, Xia Hu
2019 — conf
Using Deep Neural Network to Identify Cancer Survivors Living with Post-Traumatic Stress Disorder on Social Media.
SEPDA@ISWC
Nur Hafieza Ismail, Ninghao Liu, Mengnan Du, Zhe He, Xia Hu
2019 A* conf
XFake: Explainable Fake News Detector with Visualizations.
WWW
Fan Yang, Shiva K. Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric D. Ragan, Shuiwang Ji, Xia (Ben) Hu
2019 J jnl
XFake: Explainable Fake News Detector with Visualizations.
CoRR
Fan Yang, Shiva K. Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric D. Ragan, Shuiwang Ji, Xia (Ben) Hu
2018 J jnl
Techniques for Interpretable Machine Learning.
CoRR
Mengnan Du, Ninghao Liu, Xia Hu
2018 A* conf
Towards Explanation of DNN-based Prediction with Guided Feature Inversion.
KDD
Mengnan Du, Ninghao Liu, Qingquan Song, Xia Hu
2018 J jnl
Towards Explanation of DNN-based Prediction with Guided Feature Inversion.
CoRR
Mengnan Du, Ninghao Liu, Qingquan Song, Xia Hu
2017 J jnl
Supervised training and contextually guided salient object detection.
Digit. Signal Process.
Mengnan Du, Xingming Wu, Weihai Chen, Zhengguo Li
2016 J jnl
Exploiting multiple contexts for saliency detection.
J. Electronic Imaging
Mengnan Du, Xingming Wu, Weihai Chen, Jianhua Wang
2016 J jnl
Salient object detection via region contrast and graph regularization.
Sci. China Inf. Sci.
Xingming Wu, Mengnan Du, Weihai Chen, Jianhua Wang