Author name cluster

Zirui Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

18 papers

1 author row

AAAI Conference 2026 Conference Paper

From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation

Qingchuan Li
Mingyue Cheng
Zirui Liu
Daoyu Wang
Yuting Zeng
Tongxuan Liu

Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, underpinning scientific discovery, mathematical theorem proving, and complex decision-making. Despite the remarkable progress of large language models (LLMs), most current approaches still rely on forward reasoning paradigms, generating step-by-step rationales from premises to conclusions. However, such methods often suffer from redundant inference paths, hallucinated steps, and semantic drift, resulting in inefficient and unreliable reasoning. In this paper, we propose a novel framework, Hypothesis-driven Backward Logical Reasoning (HBLR). The core idea is to integrate confidence-aware symbolic translation with hypothesis-driven backward reasoning. In the translation phase, only high-confidence spans are converted into logical form, such as first-order logic (FOL), while uncertain content remains in natural language. A translation reflection module further ensures semantic fidelity by evaluating symbolic outputs and reverting lossy ones back to text when necessary. In the reasoning phase, HBLR simulates human deductive thinking by assuming the conclusion is true and recursively verifying its premises. A reasoning reflection module further identifies and corrects flawed inference steps, enhancing logical coherence. Extensive experiments on five reasoning benchmarks demonstrate that HBLR consistently outperforms strong baselines in both accuracy and efficiency.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

A Closed-Form Solution for Fast and Reliable Adaptive Testing

Yan Zhuang
Chenye Ke
Zirui Liu
Qi Liu
Yuting Ning
Zhenya Huang
Weizhe Huang
Qingyang Mao

Human ability estimation is essential for educational assessment, career advancement, and professional certification. Adaptive Testing systems can improve estimation efficiency by selecting fewer, targeted questions, and are widely used in exams, e. g. , GRE, GMAT, and Duolingo English Test. However, selecting an optimal subset of questions remains a challenging nested optimization problem. Existing methods rely on costly approximations or data-intensive training, making them unsuitable for today's large-scale and complex testing environments. Thus, we propose a Closed-Form solution for question subset selection in Adaptive Testing. It directly minimizes ability estimation error by reducing ability parameter's gradient bias while maintaining Hessian stability, which enables a simple greedy algorithm for question selection. Moreover, it can quantify the impact of human behavioral perturbations on ability estimation. Extensive experiments on large-scale educational datasets demonstrate that it reduces the number of required questions by 10% compared to SOTA methods, while maintaining the same estimation accuracy.

PDF Details

NeurIPS Conference 2025 Conference Paper

Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining

Haochen Zhang
Junze Yin
Guanchu Wang
Zirui Liu
Lin Yang
Tianyi Zhang
Anshumali Shrivastava
Vladimir Braverman

Low-rank optimization has emerged as a promising approach to enabling memory-efficient training of large language models (LLMs). Existing low-rank optimization methods typically project gradients onto a low-rank subspace, reducing the memory cost of storing optimizer states. A key challenge in these methods is selecting suitable subspaces to ensure an effective optimization trajectory. Most existing approaches select the dominant subspace to preserve gradient information, as this intuitively provides the best approximation. However, we find that in practice, the dominant subspace stops changing during pretraining, thereby constraining weight updates to similar subspaces. In this paper, we propose importance sampling for low-rank optimization in LLM pretraining with a provable convergence guarantee, which the dominant subspace approach does not have. Empirically, we demonstrate that our method significantly outperforms previous methods in LLM pretraining tasks.

PDF Details

AAAI Conference 2025 Conference Paper

Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages

Zihao Li
Yucheng Shi
Zirui Liu
Fan Yang
Ali Payani
Ninghao Liu
Mengnan Du

The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate. Currently, there is a lack of quantitative methods to evaluate the performance of LLMs in these low-resource languages. To address this gap, we propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using internal representations. By comparing the LLM's internal representation of various languages against a baseline derived from English, we can assess the model's multilingual capabilities in a robust and language-agnostic manner. Our analysis reveals that high-resource languages exhibit higher similarity scores with English, demonstrating superior performance, while low-resource languages show lower similarity scores, underscoring the effectiveness of our metric in assessing language-specific capabilities. Besides, the experiments show that there is a strong correlation between the LLM’s performance in different languages and the proportion of those languages in its pre-training corpus. These insights underscore the efficacy of the Language Ranker as a tool for evaluating LLM performance across different languages, particularly those with limited resources.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning

Wang Yang
Zirui Liu
Hongye Jin
Qingyu Yin
Vipin Chaudhary
Xiaotian Han

Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient long-context capacity, motivated by empirical observations such as i) higher context window length often leads to stronger reasoning performance, and ii) failed reasoning cases resemble failed long-context cases. To test this hypothesis, we examine whether enhancing a model’s long-context ability before Supervised Fine-Tuning (SFT) leads to improved reasoning performance. Specifically, we compared models with identical architectures and fine-tuning data but varying levels of long-context capacity. Our results reveal a consistent trend: models with stronger long-context capacity achieve significantly higher accuracy on reasoning benchmarks after SFT. Notably, these gains persist even on tasks with short input lengths, indicating that long-context training offers generalizable benefits for reasoning performance. These findings suggest that long-context modeling is not just essential for processing lengthy inputs, but also serves as a critical foundation for reasoning. We advocate for treating long-context capacity as a first-class objective in the design of future language models.

PDF Details

NeurIPS Conference 2025 Conference Paper

Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

Jiayi Yuan
Hao Li
Xinheng Ding
Wenya Xie
Yu-Jhe Li
Wentian Zhao
Kun Wan
Jing Shi

Large Language Models (LLMs) are now integral across various domains and have demonstrated impressive performance. Progress, however, rests on the premise that benchmark scores are both accurate and reproducible. We demonstrate that the reproducibility of LLM performance is fragile: changing system configuration, such as evaluation batch size, GPU count, and GPU version, can introduce significant differences in the generated responses. This issue is especially pronounced in reasoning models, where minor rounding differences in early tokens can cascade into divergent chains of thought, ultimately affecting accuracy. For instance, under bfloat16 precision with greedy decoding, a reasoning model like DeepSeek-R1-Distill-Qwen-7B can exhibit up to 9\% variation in accuracy and 9, 000 tokens difference in response length due to differences in GPU count, type, and evaluation batch size. We trace the root cause of this variability to the non-associative nature of floating-point arithmetic under limited numerical precision. This work presents the first systematic investigation into how numerical precision affects reproducibility in LLM inference. Through carefully controlled experiments across various hardware, software, and precision settings, we quantify when and how model outputs diverge. Our analysis reveals that floating-point precision—while critical for reproducibility—is often neglected in evaluation practices. Inspired by this, we develop a lightweight inference pipeline, dubbed LayerCast, that stores weights in 16-bit precision but performs all computations in FP32, balancing memory efficiency with numerical stability. Code is available at https: //github. com/nanomaoli/llm_reproducibility.

PDF Details

AAAI Conference 2024 Conference Paper

Chasing Fairness in Graphs: A GNN Architecture Perspective

Zhimeng Jiang
Xiaotian Han
Chao Fan
Zirui Liu
Na Zou
Ali Mostafavi
Xia Hu

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.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Computerized Adaptive Testing via Collaborative Ranking

Zirui Liu
Yan Zhuang
Qi Liu
Jiatong Li
Yuren Zhang
Zhenya Huang
Jinze Wu
Shijin Wang

As the deep integration of machine learning and intelligent education, Computerized Adaptive Testing (CAT) has received more and more research attention. Compared to traditional paper-and-pencil tests, CAT can deliver both personalized and interactive assessments by automatically adjusting testing questions according to the performance of students during the test process. Therefore, CAT has been recognized as an efficient testing methodology capable of accurately estimating a student’s ability with a minimal number of questions, leading to its widespread adoption in mainstream selective exams such as the GMAT and GRE. However, just improving the accuracy of ability estimation is far from satisfactory in the real-world scenarios, since an accurate ranking of students is usually more important (e. g. , in high-stakes exams). Considering the shortage of existing CAT solutions in student ranking, this paper emphasizes the importance of aligning test outcomes (student ranks) with the true underlying abilities of students. Along this line, different from the conventional independent testing paradigm among students, we propose a novel collaborative framework, Collaborative Computerized Adaptive Testing (CCAT), that leverages inter-student information to enhance student ranking. By using collaborative students as anchors to assist in ranking test-takers, CCAT can give both theoretical guarantees and experimental validation for ensuring ranking consistency.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Gradient Rewiring for Editable Graph Neural Network Training

Zhimeng Jiang
Zirui Liu
Xiaotian Han
Qizhang Feng
Hongye Jin
Qiaoyu Tan
Kaixiong Zhou
Na Zou

Deep neural networks are ubiquitously adopted in many applications, such as computer vision, natural language processing, and graph analytics. However, well-trained neural networks can make prediction errors after deployment as the world changes. \textit{Model editing} involves updating the base model to correct prediction errors with less accessible training data and computational resources. Despite recent advances in model editors in computer vision and natural language processing, editable training in graph neural networks (GNNs) is rarely explored. The challenge with editable GNN training lies in the inherent information aggregation across neighbors, which can lead model editors to affect the predictions of other nodes unintentionally. In this paper, we first observe the gradient of cross-entropy loss for the target node and training nodes with significant inconsistency, which indicates that directly fine-tuning the base model using the loss on the target node deteriorates the performance on training nodes. Motivated by the gradient inconsistency observation, we propose a simple yet effective \underline{G}radient \underline{R}ewiring method for \underline{E}ditable graph neural network training, named \textbf{GRE}. Specifically, we first store the anchor gradient of the loss on training nodes to preserve the locality. Subsequently, we rewire the gradient of the loss on the target node to preserve performance on the training node using anchor gradient. Experiments demonstrate the effectiveness of GRE on various model architectures and graph datasets in terms of multiple editing situations. The source code is available at \url{https: //github. com/zhimengj0326/Gradient rewiring editing}.

PDF Details DOI

TMLR Journal 2023 Journal Article

DSpar: An Embarrassingly Simple Strategy for Efficient GNN training and inference via Degree-based Sparsification

Zirui Liu
Kaixiong Zhou
Zhimeng Jiang
Li Li
Rui Chen
Soo-Hyun Choi
Xia Hu

Running Graph Neural Networks (GNNs) on large graphs suffers from notoriously inefficiency. This is attributed to the sparse graph-based operations, which is hard to be accelerated by community hardware, e.g., GPUs and CPUs. One potential solution is to ``sketch'' the original graph by removing unimportant edges, then both the training and inference process are executed on the sparsified graph with improved efficiency. Traditional graph sparsification work calculates the edge importance score, i.e., effective resistance, from graph topology with theoretical guarantee. However, estimating effective resistance is even more expensive than training GNNs itself. Later, learning-based sparsification methods propose to learn the edge importance from data, but with significant overhead due to the extra learning process. Thus, both of them introduce significant ahead-of-training overhead. In this paper, we experimentally and theoretically prove that effective resistance can be approximated using only the node degree information and achieve similar node presentations on graph with/without sparsification. Based on this finding, we propose DSpar, to sparsify the graph once before training based on only the node degree information with negligible ahead-of-training overhead. In practice, for the training phase, DSpar achieves up to $5.9\times$ faster than baseline with almost no accuracy drop. For the inference phase, DSpar reduces up to $90\%$ latency.

PDF Details

NeurIPS Conference 2023 Conference Paper

One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning

Shaochen (Henry) Zhong
Zaichuan You
Jiamu Zhang
Sebastian Zhao
Zachary LeClaire
Zirui Liu
Daochen Zha
Vipin Chaudhary

Densely structured pruning methods utilizing simple pruning heuristics can deliver immediate compression and acceleration benefits with acceptable benign performances. However, empirical findings indicate such naively pruned networks are extremely fragile under simple adversarial attacks. Naturally, we would be interested in knowing if such a phenomenon also holds for carefully designed modern structured pruning methods. If so, then to what extent is the severity? And what kind of remedies are available? Unfortunately, both the questions and the solution remain largely unaddressed: no prior art is able to provide a thorough investigation on the adversarial performance of modern structured pruning methods (spoiler: it is not good), yet the few works that attempt to provide mitigation often do so at various extra costs with only to-be-desired performance. In this work, we answer both questions by fairly and comprehensively investigating the adversarial performance of 10+ popular structured pruning methods. Solution-wise, we take advantage of Grouped Kernel Pruning (GKP) 's recent success in pushing densely structured pruning freedom to a more fine-grained level. By mixing up kernel smoothness — a classic robustness-related kernel-level metric — into a modified GKP procedure, we present a one-shot-post-train-weight-dependent GKP method capable of advancing SOTA performance on both the benign and adversarial scale, while requiring no extra (in fact, often less) cost than a standard pruning procedure. Please refer to our GitHub repository for code implementation, tool sharing, and model checkpoints.

PDF Details

TMLR Journal 2023 Journal Article

Retiring $\Delta \text{DP}$: New Distribution-Level Metrics for Demographic Parity

Xiaotian Han
Zhimeng Jiang
Hongye Jin
Zirui Liu
Na Zou
Qifan Wang
Xia Hu

Demographic parity is the most widely recognized measure of group fairness in machine learning, which ensures equal treatment of different demographic groups. Numerous works aim to achieve demographic parity by pursuing the commonly used metric $\Delta DP$. Unfortunately, in this paper, we reveal that the fairness metric $\Delta DP$ can not precisely measure the violation of demographic parity, because it inherently has the following drawbacks: i) zero-value $\Delta DP$ does not guarantee zero violation of demographic parity, ii) $\Delta DP$ values can vary with different classification thresholds. To this end, we propose two new fairness metrics, Area Between Probability density function Curves (ABPC) and Area Between Cumulative density function Curves (ABCC), to precisely measure the violation of demographic parity at the distribution level. The new fairness metrics directly measure the difference between the distributions of the prediction probability for different demographic groups. Thus our proposed new metrics enjoy: i) zero-value ABCC/ABPC guarantees zero violation of demographic parity; ii) ABCC/ABPC guarantees demographic parity while the classification thresholds are adjusted. We further re-evaluate the existing fair models with our proposed fairness metrics and observe different fairness behaviors of those models under the new metrics.

PDF Details

NeurIPS Conference 2023 Conference Paper

Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

Ruixiang (Ryan) Tang
Jiayi Yuan
Yiming Li
Zirui Liu
Rui Chen
Xia Hu

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the adversaries can embed malicious prediction behaviors by manipulating a few training samples. In this study, our objective is to develop a backdoor-resistant tuning procedure that yields a backdoor-free model, no matter whether the fine-tuning dataset contains poisoned samples. To this end, we propose and integrate an \emph{honeypot module} into the original PLM, specifically designed to absorb backdoor information exclusively. Our design is motivated by the observation that lower-layer representations in PLMs carry sufficient backdoor features while carrying minimal information about the original tasks. Consequently, we can impose penalties on the information acquired by the honeypot module to inhibit backdoor creation during the fine-tuning process of the stem network. Comprehensive experiments conducted on benchmark datasets substantiate the effectiveness and robustness of our defensive strategy. Notably, these results indicate a substantial reduction in the attack success rate ranging from 10\% to 40\% when compared to prior state-of-the-art methods.

PDF Details

NeurIPS Conference 2023 Conference Paper

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

Zirui Liu
Guanchu Wang
Shaochen (Henry) Zhong
Zhaozhuo Xu
Daochen Zha
Ruixiang (Ryan) Tang
Zhimeng (Stephen) Jiang
Kaixiong Zhou

As the model size grows rapidly, fine-tuning the large pre-trained language model has become increasingly difficult due to its extensive memory usage. Previous works usually focus on reducing the number of trainable parameters in the network. While the model parameters do contribute to memory usage, the primary memory bottleneck during training arises from storing feature maps, also known as activations, as they are crucial for gradient calculation. Notably, machine learning models are typically trained using stochastic gradient descent. We argue that in stochastic optimization, models can handle noisy gradients as long as the gradient estimator is unbiased with reasonable variance. Following this motivation, we propose a new family of unbiased estimators called \sas, for matrix production with reduced variance, which only requires storing the sub-sampled activations for calculating the gradient. Our work provides both theoretical and experimental evidence that, in the context of tuning transformers, our proposed estimators exhibit lower variance compared to existing ones. By replacing the linear operation with our approximated one in transformers, we can achieve up to 2. 7X peak memory reduction with almost no accuracy drop and enables up to $6. 4\times$ larger batch size. Under the same hardware, \sas enables better down-streaming task performance by applying larger models and/or faster training speed with larger batch sizes. The code is available at https: //anonymous. 4open. science/r/WTACRS-A5C5/.

PDF Details

NeurIPS Conference 2022 Conference Paper

A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking

Keyu Duan
Zirui Liu
Peihao Wang
Wenqing Zheng
Kaixiong Zhou
Tianlong Chen
Xia Hu
Zhangyang Wang

Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs). Due to the nature of evolving graph structures into the training process, vanilla GNNs usually fail to scale up, limited by the GPU memory space. Up to now, though numerous scalable GNN architectures have been proposed, we still lack a comprehensive survey and fair benchmark of this reservoir to find the rationale for designing scalable GNNs. To this end, we first systematically formulate the representative methods of large-scale graph training into several branches and further establish a fair and consistent benchmark for them by a greedy hyperparameter searching. In addition, regarding efficiency, we theoretically evaluate the time and space complexity of various branches and empirically compare them w. r. t GPU memory usage, throughput, and convergence. Furthermore, We analyze the pros and cons for various branches of scalable GNNs and then present a new ensembling training manner, named EnGCN, to address the existing issues. Remarkably, our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets. Our code is available at https: //github. com/VITA-Group/Large Scale GCN_Benchmarking.

PDF Details

NeurIPS Conference 2022 Conference Paper

DreamShard: Generalizable Embedding Table Placement for Recommender Systems

Daochen Zha
Louis Feng
Qiaoyu Tan
Zirui Liu
Kwei-Herng Lai
Bhargav Bhushanam
Yuandong Tian
Arun Kejariwal

We study embedding table placement for distributed recommender systems, which aims to partition and place the tables on multiple hardware devices (e. g. , GPUs) to balance the computation and communication costs. Although prior work has explored learning-based approaches for the device placement of computational graphs, embedding table placement remains to be a challenging problem because of 1) the operation fusion of embedding tables, and 2) the generalizability requirement on unseen placement tasks with different numbers of tables and/or devices. To this end, we present DreamShard, a reinforcement learning (RL) approach for embedding table placement. DreamShard achieves the reasoning of operation fusion and generalizability with 1) a cost network to directly predict the costs of the fused operation, and 2) a policy network that is efficiently trained on an estimated Markov decision process (MDP) without real GPU execution, where the states and the rewards are estimated with the cost network. Equipped with sum and max representation reductions, the two networks can directly generalize to any unseen tasks with different numbers of tables and/or devices without fine-tuning. Extensive experiments show that DreamShard substantially outperforms the existing human expert and RNN-based strategies with up to 19% speedup over the strongest baseline on large-scale synthetic tables and our production tables. The code is available.

PDF Details

IJCAI Conference 2022 Conference Paper

Table2Graph: Transforming Tabular Data to Unified Weighted Graph

Kaixiong Zhou
Zirui Liu
Rui Chen
Li Li
Soo-Hyun Choi
Xia Hu

Learning useful interactions between input features is crucial for tabular data modeling. Recent efforts start to explicitly model the feature interactions with graph, where each feature is treated as an individual node. However, the existing graph construction methods either heuristically formulate a fixed feature-interaction graph based on specific domain knowledge, or simply apply attention function to compute the pairwise feature similarities for each sample. While the fixed graph may be sub-optimal to downstream tasks, the sample-wise graph construction is time-consuming during model training and inference. To tackle these issues, we propose a framework named Table2Graph to transform the feature interaction modeling to learning a unified graph. Represented as a probability adjacency matrix, the unified graph learns to model the key feature interactions shared by the diverse samples in the tabular data. To well optimize the unified graph, we employ the reinforcement learning policy to capture the key feature interactions stably. A sparsity constraint is also proposed to regularize the learned graph from being overly-sparse/smooth. The experimental results in a variety of real-world applications demonstrate the effectiveness and efficiency of our Table2Graph, in terms of the prediction accuracy and feature interaction detection.

PDF Details DOI

NeurIPS Conference 2020 Conference Paper

Detecting Interactions from Neural Networks via Topological Analysis

Zirui Liu
Qingquan Song
Kaixiong Zhou
Ting-Hsiang Wang
Ying Shan
Xia Hu

Detecting statistical interactions between input features is a crucial and challenging task. Recent advances demonstrate that it is possible to extract learned interactions from trained neural networks. It has also been observed that, in neural networks, any interacting features must follow a strongly weighted connection to common hidden units. Motivated by the observation, in this paper, we propose to investigate the interaction detection problem from a novel topological perspective by analyzing the connectivity in neural networks. Specially, we propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology. Based on this measure, a Persistence Interaction Dection (PID) algorithm is developed to efficiently detect interactions. Our proposed algorithm is evaluated across a number of interaction detection tasks on several synthetic and real-world datasets with different hyperparameters. Experimental results validate that the PID algorithm outperforms the state-of-the-art baselines.

PDF Details