Na Zou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Na Zou has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Ali Mostafavi
Texas A&M University
2 shared publications - Chao Fan
School of Civil and Environmental Engineering and Earth Sciences, Clemson University, Clemson, USA
2 shared publications - Chia-Yuan Chang
Texas A&M University
2 shared publications - Mingzhi Hu
Worcester Polytechnic Institute
2 shared publications Vineeth Rakesh
Visa Research
2 shared publications- Xia Hu
Rice University, Houston, TX, USA
2 shared publications
Latest Publications
- 25 June 2025
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 9 (4) , 703-719
FairAlloc: Learning Fair Organ Allocation Policy for Liver Transplant
Liver transplantation is a critical treatment for end-stage liver diseases, but ensuring fair and effective allocation of scarce donor organs remains a major challenge in healthcare. Existing allocation policies often struggle to balance clinical outcomes with fairness across patients and demographic groups. To address this, we propose FairAlloc, a learning-based framework that formulates organ allocation as a ranking problem and jointly optimizes for post-transplant outcomes and fairness. Specifically, FairAlloc integrates two fairness objectives—group fairness across sensitive attributes such as gender and race and individual fairness between similar patients—into the ranking process. We evaluate FairAlloc using real-world data from the Organ Procurement and Transplantation Network (OPTN) and compare its performance to six baseline methods. Results show that FairAlloc improves group and individual fairness metrics by up to 37.9% and 39.9%, respectively, while maintaining competitive performance on key post-transplant outcomes such as graft failure and survival rates. This work contributes a novel, fairness-aware decision-making framework to the healthcare informatics community, with the potential to improve equity and efficiency in organ allocation systems.
- 25 June 2025
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 9 (4) , 703-719
FairAlloc: Learning Fair Organ Allocation Policy for Liver Transplant
Liver transplantation is a critical treatment for end-stage liver diseases, but ensuring fair and effective allocation of scarce donor organs remains a major challenge in healthcare. Existing allocation policies often struggle to balance clinical outcomes with fairness across patients and demographic groups. To address this, we propose FairAlloc, a learning-based framework that formulates organ allocation as a ranking problem and jointly optimizes for post-transplant outcomes and fairness. Specifically, FairAlloc integrates two fairness objectives—group fairness across sensitive attributes such as gender and race and individual fairness between similar patients—into the ranking process. We evaluate FairAlloc using real-world data from the Organ Procurement and Transplantation Network (OPTN) and compare its performance to six baseline methods. Results show that FairAlloc improves group and individual fairness metrics by up to 37.9% and 39.9%, respectively, while maintaining competitive performance on key post-transplant outcomes such as graft failure and survival rates. This work contributes a novel, fairness-aware decision-making framework to the healthcare informatics community, with the potential to improve equity and efficiency in organ allocation systems.
- Top Cited PapersOpen Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 2607-2622
MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
Chia-Yuan Chang, Zhimeng Jiang, Vineeth Rakesh, Menghai Pan, Chin-Chia Michael Yeh, Guanchu Wang, Mingzhi Hu, Zhichao Xu, Yan Zheng, Mahashweta Das, Na Zou. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 2607-2622
Top Cited PapersOpen AccessMAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
Chia-Yuan Chang, Zhimeng Jiang, Vineeth Rakesh, Menghai Pan, Chin-Chia Michael Yeh, Guanchu Wang, Mingzhi Hu, Zhichao Xu, Yan Zheng, Mahashweta Das, Na Zou. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 30503-30517
Quantized Can Still Be Calibrated: A Unified Framework to Calibration in Quantized Large Language Models
Mingyu Zhong, Guanchu Wang, Yu-Neng Chuang, Na Zou. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 30503-30517
Open AccessQuantized Can Still Be Calibrated: A Unified Framework to Calibration in Quantized Large Language Models
Mingyu Zhong, Guanchu Wang, Yu-Neng Chuang, Na Zou. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
Large Language Models (LLMs) are becoming essential tools for various natural language processing tasks but often suffer from generating outdated or incorrect information. Retrieval-Augmented Generation (RAG) addresses this issue by incorporating external, real-time information retrieval to ground LLM responses. However, the existing RAG systems frequently struggle with the quality of retrieval documents, as irrelevant or noisy documents degrade performance, increase computational overhead, and undermine response reliability. To tackle this problem, we propose Multi-Agent Filtering Retrieval-Augmented Generation (MAIN-RAG), a training-free RAG framework that leverages multiple LLM agents to collaboratively filter and score retrieved documents. Specifically, MAIN-RAG introduces an adaptive filtering mechanism that dynamically adjusts the relevance filtering threshold based on score distributions, effectively minimizing noise while maintaining high recall of relevant documents. The proposed approach leverages inter-agent consensus to ensure robust document selection without requiring additional training data or fine-tuning. Experimental results across four QA benchmarks demonstrate that MAIN-RAG consistently outperforms traditional RAG approaches, achieving a 2-11% improvement in answer accuracy while reducing the number of irrelevant retrieved documents. Quantitative analysis further reveals that our approach achieves superior response consistency and answer accuracy over baseline methods, offering a competitive and practical alternative to training-based solutions.
Open AccessMAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
Large Language Models (LLMs) are becoming essential tools for various natural language processing tasks but often suffer from generating outdated or incorrect information. Retrieval-Augmented Generation (RAG) addresses this issue by incorporating external, real-time information retrieval to ground LLM responses. However, the existing RAG systems frequently struggle with the quality of retrieval documents, as irrelevant or noisy documents degrade performance, increase computational overhead, and undermine response reliability. To tackle this problem, we propose Multi-Agent Filtering Retrieval-Augmented Generation (MAIN-RAG), a training-free RAG framework that leverages multiple LLM agents to collaboratively filter and score retrieved documents. Specifically, MAIN-RAG introduces an adaptive filtering mechanism that dynamically adjusts the relevance filtering threshold based on score distributions, effectively minimizing noise while maintaining high recall of relevant documents. The proposed approach leverages inter-agent consensus to ensure robust document selection without requiring additional training data or fine-tuning. Experimental results across four QA benchmarks demonstrate that MAIN-RAG consistently outperforms traditional RAG approaches, achieving a 2-11% improvement in answer accuracy while reducing the number of irrelevant retrieved documents. Quantitative analysis further reveals that our approach achieves superior response consistency and answer accuracy over baseline methods, offering a competitive and practical alternative to training-based solutions.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (19) , 21214-21222
Chasing Fairness in Graphs: A GNN Architecture Perspective
There has been significant progress in improving the performance of graph neural networks (GNNs) through enhancements in graph data, model architecture design, and training strategies. For fairness in graphs, recent studies achieve fair representations and predictions through either graph data pre-processing (e.g., node feature masking, and topology rewiring) or fair training strategies (e.g., regularization, adversarial debiasing, and fair contrastive learning). How to achieve fairness in graphs from the model architecture perspective is less explored. More importantly, GNNs exhibit worse fairness performance compared to multilayer perception since their model architecture (i.e., neighbor aggregation) amplifies biases. To this end, we aim to achieve fairness via a new GNN architecture. We propose Fair Message Passing (FMP) designed within a unified optimization framework for GNNs. Notably, FMP explicitly renders sensitive attribute usage in forward propagation for node classification task using cross-entropy loss without data pre-processing. In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. In this way, FMP scheme can aggregate useful information from neighbors and mitigate bias to achieve better fairness and prediction tradeoff performance. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets. The code is available at https://github.com/zhimengj0326/FMP.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (19) , 21214-21222
Open AccessChasing Fairness in Graphs: A GNN Architecture Perspective
There has been significant progress in improving the performance of graph neural networks (GNNs) through enhancements in graph data, model architecture design, and training strategies. For fairness in graphs, recent studies achieve fair representations and predictions through either graph data pre-processing (e.g., node feature masking, and topology rewiring) or fair training strategies (e.g., regularization, adversarial debiasing, and fair contrastive learning). How to achieve fairness in graphs from the model architecture perspective is less explored. More importantly, GNNs exhibit worse fairness performance compared to multilayer perception since their model architecture (i.e., neighbor aggregation) amplifies biases. To this end, we aim to achieve fairness via a new GNN architecture. We propose Fair Message Passing (FMP) designed within a unified optimization framework for GNNs. Notably, FMP explicitly renders sensitive attribute usage in forward propagation for node classification task using cross-entropy loss without data pre-processing. In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. In this way, FMP scheme can aggregate useful information from neighbors and mitigate bias to achieve better fairness and prediction tradeoff performance. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets. The code is available at https://github.com/zhimengj0326/FMP.
- Open Access
Chasing Fairness in Graphs: A GNN Architecture Perspective
There has been significant progress in improving the performance of graph neural networks (GNNs) through enhancements in graph data, model architecture design, and training strategies. For fairness in graphs, recent studies achieve fair representations and predictions through either graph data pre-processing (e.g., node feature masking, and topology rewiring) or fair training strategies (e.g., regularization, adversarial debiasing, and fair contrastive learning). How to achieve fairness in graphs from the model architecture perspective is less explored. More importantly, GNNs exhibit worse fairness performance compared to multilayer perception since their model architecture (i.e., neighbor aggregation) amplifies biases. To this end, we aim to achieve fairness via a new GNN architecture. We propose \textsf{F}air \textsf{M}essage \textsf{P}assing (FMP) designed within a unified optimization framework for GNNs. Notably, FMP \textit{explicitly} renders sensitive attribute usage in \textit{forward propagation} for node classification task using cross-entropy loss without data pre-processing. In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. In this way, FMP scheme can aggregate useful information from neighbors and mitigate bias to achieve better fairness and prediction tradeoff performance. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets. The code is available in {\url{https://github.com/zhimengj0326/FMP}}.
Open AccessChasing Fairness in Graphs: A GNN Architecture Perspective
There has been significant progress in improving the performance of graph neural networks (GNNs) through enhancements in graph data, model architecture design, and training strategies. For fairness in graphs, recent studies achieve fair representations and predictions through either graph data pre-processing (e.g., node feature masking, and topology rewiring) or fair training strategies (e.g., regularization, adversarial debiasing, and fair contrastive learning). How to achieve fairness in graphs from the model architecture perspective is less explored. More importantly, GNNs exhibit worse fairness performance compared to multilayer perception since their model architecture (i.e., neighbor aggregation) amplifies biases. To this end, we aim to achieve fairness via a new GNN architecture. We propose \textsf{F}air \textsf{M}essage \textsf{P}assing (FMP) designed within a unified optimization framework for GNNs. Notably, FMP \textit{explicitly} renders sensitive attribute usage in \textit{forward propagation} for node classification task using cross-entropy loss without data pre-processing. In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. In this way, FMP scheme can aggregate useful information from neighbors and mitigate bias to achieve better fairness and prediction tradeoff performance. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets. The code is available in {\url{https://github.com/zhimengj0326/FMP}}.