arXiv subjects

Wenxin Zhou

Publications and source records attributed to Wenxin Zhou.

8 recordsLinked to original sources

arXiv2026

Remaining-data-free Machine Unlearning by Suppressing Sample Contribution

Machine unlearning (MU) aims to remove the influence of specific training samples from a well-trained model, a task of growing importance due to the ``right to be forgotten.'' The unlearned model should approach the retrained model, where forgetting data do not contribute to the training process. Therefore, unlearning should withdraw their contribution from the pre-trained model. However, quantifying and disentangling sample's contribution to overall learning process is highly challenging, leading most existing MU approaches to adopt other heuristic strategies such as random labeling or knowledge distillation. These operations inevitably degrade model utility, requiring additional maintenance with remaining data. To advance MU towards better utility and efficiency for practical deployment, we seek to approximate sample contribution with only the pre-trained model. We theoretically and empirically reveal that sample's contribution during training manifests in the learned model's increased sensitivity to it. In light of this, we propose MU-Mis (Machine Unlearning by Minimizing input sensitivity), which directly suppresses the contribution of forgetting data. This straightforward suppression enables MU-Mis to successfully unlearn without degrading model utility on the remaining data, thereby eliminating the need for access to the remaining data. To the best of our knowledge, this is the first time that a remaining-data-free method can perform on par with top performing remaining-data-dependent methods.

cs.LG↗

arXiv2026

DS@GT at TREC TOT 2025: Bridging Vague Recollection with Fusion Retrieval and Learned Reranking

We develop a two-stage retrieval system that combines multiple complementary retrieval methods with a learned reranker and LLM-based reranking, to address the TREC Tip-of-the-Tongue (ToT) task. In the first stage, we employ hybrid retrieval that merges LLM-based retrieval, sparse (BM25), and dense (BGE-M3) retrieval methods. We also introduce topic-aware multi-index dense retrieval that partitions the Wikipedia corpus into 24 topical domains. In the second stage, we evaluate both a trained LambdaMART reranker and LLM-based reranking. To support model training, we generate 5000 synthetic ToT queries using LLMs. Our best system achieves recall of 0.66 and NDCG@1000 of 0.41 on the test set by combining hybrid retrieval with Gemini-2.5-flash reranking, demonstrating the effectiveness of fusion retrieval.

cs.IR↗

arXiv2024

Using Pretrained Large Language Model with Prompt Engineering to Answer Biomedical Questions

Our team participated in the BioASQ 2024 Task12b and Synergy tasks to build a system that can answer biomedical questions by retrieving relevant articles and snippets from the PubMed database and generating exact and ideal answers. We propose a two-level information retrieval and question-answering system based on pre-trained large language models (LLM), focused on LLM prompt engineering and response post-processing. We construct prompts with in-context few-shot examples and utilize post-processing techniques like resampling and malformed response detection. We compare the performance of various pre-trained LLM models on this challenge, including Mixtral, OpenAI GPT and Llama2. Our best-performing system achieved 0.14 MAP score on document retrieval, 0.05 MAP score on snippet retrieval, 0.96 F1 score for yes/no questions, 0.38 MRR score for factoid questions and 0.50 F1 score for list questions in Task 12b.

cs.CL↗

arXiv2024

Biomedical Nested NER with Large Language Model and UMLS Heuristics

In this paper, we present our system for the BioNNE English track, which aims to extract 8 types of biomedical nested named entities from biomedical text. We use a large language model (Mixtral 8x7B instruct) and ScispaCy NER model to identify entities in an article and build custom heuristics based on unified medical language system (UMLS) semantic types to categorize the entities. We discuss the results and limitations of our system and propose future improvements. Our system achieved an F1 score of 0.39 on the BioNNE validation set and 0.348 on the test set.

cs.CL↗

arXiv2023

Deconstructing Student Perceptions of Generative AI (GenAI) through an Expectancy Value Theory (EVT)-based Instrument

This study examines the relationship between student perceptions and their intention to use generative AI in higher education. Drawing on Expectancy-Value Theory (EVT), a questionnaire was developed to measure students' knowledge of generative AI, perceived value, and perceived cost. A sample of 405 students participated in the study, and confirmatory factor analysis was used to validate the constructs. The results indicate a strong positive correlation between perceived value and intention to use generative AI, and a weak negative correlation between perceived cost and intention to use. As we continue to explore the implications of generative AI in education and other domains, it is crucial to carefully consider the potential long-term consequences and the ethical dilemmas that may arise from widespread adoption.

cs.CY↗

arXiv2021

Distributed Adaptive Huber Regression

Distributed data naturally arise in scenarios involving multiple sources of observations, each stored at a different location. Directly pooling all the data together is often prohibited due to limited bandwidth and storage, or due to privacy protocols. This paper introduces a new robust distributed algorithm for fitting linear regressions when data are subject to heavy-tailed and/or asymmetric errors with finite second moments. The algorithm only communicates gradient information at each iteration and therefore is communication-efficient. Statistically, the resulting estimator achieves the centralized nonasymptotic error bound as if all the data were pooled together and came from a distribution with sub-Gaussian tails. Under a finite $(2+δ)$-th moment condition, we derive a Berry-Esseen bound for the distributed estimator, based on which we construct robust confidence intervals. Numerical studies further confirm that compared with extant distributed methods, the proposed methods achieve near-optimal accuracy with low variability and better coverage with tighter confidence width.

stat.ME↗

arXiv2018

Adaptive Huber Regression

Big data can easily be contaminated by outliers or contain variables with heavy-tailed distributions, which makes many conventional methods inadequate. To address this challenge, we propose the adaptive Huber regression for robust estimation and inference. The key observation is that the robustification parameter should adapt to the sample size, dimension and moments for optimal tradeoff between bias and robustness. Our theoretical framework deals with heavy-tailed distributions with bounded $(1+δ)$-th moment for any $δ> 0$. We establish a sharp phase transition for robust estimation of regression parameters in both low and high dimensions: when $δ\geq 1$, the estimator admits a sub-Gaussian-type deviation bound without sub-Gaussian assumptions on the data, while only a slower rate is available in the regime $0<δ< 1$. Furthermore, this transition is smooth and optimal. In addition, we extend the methodology to allow both heavy-tailed predictors and observation noise. Simulation studies lend further support to the theory. In a genetic study of cancer cell lines that exhibit heavy-tailedness, the proposed methods are shown to be more robust and predictive.

math.ST↗

arXiv2018

A Unified Framework for Testing High Dimensional Parameters: A Data-Adaptive Approach

High dimensional hypothesis test deals with models in which the number of parameters is significantly larger than the sample size. Existing literature develops a variety of individual tests. Some of them are sensitive to the dense and small disturbance, and others are sensitive to the sparse and large disturbance. Hence, the powers of these tests depend on the assumption of the alternative scenario. This paper provides a unified framework for developing new tests which are adaptive to a large variety of alternative scenarios in high dimensions. In particular, our framework includes arbitrary hypotheses which can be tested using high dimensional $U$-statistic based vectors. Under this framework, we first develop a broad family of tests based on a novel variant of the $L_p$-norm with $p\in \{1,\dots,\infty\}$. We then combine these tests to construct a data-adaptive test that is simultaneously powerful under various alternative scenarios. To obtain the asymptotic distributions of these tests, we utilize the multiplier bootstrap for $U$-statistics. In addition, we consider the computational aspect of the bootstrap method and propose a novel low-cost scheme. We prove the optimality of the proposed tests. Thorough numerical results on simulated and real datasets are provided to support our theory.

math.ST↗