Large language models (LLMs) have achieved remarkable success across widespread tasks, yet their application in low-resource domains remains a significant challenge due to data scarcity and the high risk of overfitting. While in-domain data is limited, there exist vast amounts of similar general-domain data, and our initial findings reveal that they could potentially serve as auxiliary supervision for domain enhancement. This observation leads us to our central research question: how to effectively select the most valuable auxiliary data to maximize domain-specific performance, particularly when traditional methods are inapplicable due to a lack of large in-domain data pools or validation sets. To address this, we propose NTK-Selector, a principled and efficient framework for selecting general-domain auxiliary data to enhance domain-specific performance via neural tangent kernels (NTK). Our method tackles two challenges of directly applying NTK to LLMs, theoretical assumptions and prohibitive computational cost, by empirically demonstrating a stable NTK-like behavior in LLMs during LoRA fine-tuning and proposing a Jacobian-free approximation method. Extensive experiments across four low-resource domains (medical, financial, legal, and psychological) demonstrate that NTK-Selector consistently improves downstream performance. Specifically, fine-tuning on 1,000 in-domain samples alone only yielded +0.8 points for Llama3-8B-Instruct and +0.9 points for Qwen3-8B. In contrast, enriching with 9,000 auxiliary samples selected by NTK-Selector led to substantial gains of +8.7 and +5.1 points, which corresponds to a 10.9x and 5.7x improvement over the domain-only setting. Each task is augmented with 9K auxiliary samples selected by Random, LESS, and NTK-Selector from Cot Collection based on 1K domain samples. The emergence of large language models (LLMs) has led to remarkable advancements across a wide spectrum of natural language processing tasks (Touvron et al., 2023; Chowdhery et al., 2023; Y ang et al., 2025). However, their formidable capabilities are predominantly anchored in the availability of immense, high-quality pre-training and instruction-tuning datasets.

A membership-inference attack gets the output of a learning algorithm, and a target individual, and tries to determine whether this individual is a member of the training data or an independent sample from the same distribution. A successful membership-inference attack typically requires the attacker to have some knowledge about the distribution that the training data was sampled from, and this knowledge is often captured through a set of independent reference samples from that distribution. In this work we study how much information the attacker needs for membership inference by investigating the sample complexity-the minimum number of reference samples required-for a successful attack. We study this question in the fundamental setting of Gaussian mean estimation where the learning algorithm is given $n$ samples from a Gaussian distribution $\mathcal{N}(μ,Σ)$ in $d$ dimensions, and tries to estimate $\hatμ$ up to some error $\mathbb{E}[\|\hat μ- μ\|^2_Σ]\leq ρ^2 d$. Our result shows that for membership inference in this setting, $Ω(n + n^2 ρ^2)$ samples can be necessary to carry out any attack that competes with a fully informed attacker. Our result is the first to show that the attacker sometimes needs many more samples than the training algorithm uses to train the model. This result has significant implications for practice, as all attacks used in practice have a restricted form that uses $O(n)$ samples and cannot benefit from $ω(n)$ samples. Thus, these attacks may be underestimating the possibility of membership inference, and better attacks may be possible when information about the distribution is easy to obtain.

Linkage analysis has provided valuable insights to the GWAS studies, particularly in revealing that SNPs in linkage disequilibrium (LD) can jointly influence disease phenotypes. However, the potential of LD network data has often been overlooked or underutilized in the literature. In this paper, we propose a locally adaptive structure learning algorithm (LASLA) that provides a principled and generic framework for incorporating network data or multiple samples of auxiliary data from related source domains; possibly in different dimensions/structures and from diverse populations. LASLA employs a $p$-value weighting approach, utilizing structural insights to assign data-driven weights to individual test points. Theoretical analysis shows that LASLA can asymptotically control FDR with independent or weakly dependent primary statistics, and achieve higher power when the network data is informative. Efficiency again of LASLA is illustrated through various synthetic experiments and an application to T2D-associated SNP identification.

The insurance industry is shifting their sales mode from offline to online, in expectation to reach massive potential customers in the digitization era. Due to the complexity and the nature of insurance products, a cost-effective online sales solution is to exploit chatbot AI to raise customers' attention and pass those with interests to human agents for further sales. For high response and conversion rates of customers, it is crucial for the chatbot to initiate a conversation with personalized opening sentences, which are generated with user-specific topic selection and ordering. Such personalized opening sentence generation is challenging because (i) there are limited historical samples for conversation topic recommendation in online insurance sales and (ii) existing text generation schemes often fail to support customized topic ordering based on user preferences. We design POSGen, a personalized opening sentence generation scheme dedicated for online insurance sales. It transfers user embeddings learned from auxiliary online user behaviours to enhance conversation topic recommendation, and exploits a context management unit to arrange the recommended topics in user-specific ordering for opening sentence generation. POSGen is deployed on a real-world online insurance platform. It achieves 2.33x total insurance premium improvement through a two-month global test.

Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to better-match the output of the student model to that of the teacher model based on the knowledge extracts from the forward pass of the teacher network. Although conventional KD is effective for matching the two networks over the given data points, there is no guarantee that these models would match in other areas for which we do not have enough training samples. In this work, we address that problem by generating new auxiliary training samples based on extracting knowledge from the backward pass of the teacher in the areas where the student diverges greatly from the teacher. We compute the difference between the teacher and the student and generate new data samples that maximize the divergence. This is done by perturbing data samples in the direction of the gradient of the difference between the student and the teacher. Augmenting the training set by adding this auxiliary improves the performance of KD significantly and leads to a closer match between the student and the teacher. Using this approach, when data samples come from a discrete domain, such as applications of natural language processing (NLP) and language understanding, is not trivial. However, we show how this technique can be used successfully in such applications. We evaluated the performance of our method on various tasks in computer vision and NLP domains and got promising results.

Federated learning (FL) has emerged as a practical solution to tackle data silo issues without compromising user privacy. One of its variants, vertical federated learning (VFL), has recently gained increasing attention as the VFL matches the enterprises' demands of leveraging more valuable features to build better machine learning models while preserving user privacy. Current works in VFL concentrate on developing a specific protection or attack mechanism for a particular VFL algorithm. In this work, we propose an evaluation framework that formulates the privacy-utility evaluation problem. We then use this framework as a guide to comprehensively evaluate a broad range of protection mechanisms against most of the state-of-the-art privacy attacks for three widely-deployed VFL algorithms. These evaluations may help FL practitioners select appropriate protection mechanisms given specific requirements. Our evaluation results demonstrate that: the model inversion and most of the label inference attacks can be thwarted by existing protection mechanisms; the model completion (MC) attack is difficult to be prevented, which calls for more advanced MC-targeted protection mechanisms. Based on our evaluation results, we offer concrete advice on improving the privacy-preserving capability of VFL systems.

Personalized optimal decision making, finding the optimal decision rule (ODR) based on individual characteristics, has attracted increasing attention recently in many fields, such as education, economics, and medicine. Current ODR methods usually require the primary outcome of interest in samples for assessing treatment effects, namely the experimental sample. However, in many studies, treatments may have a long-term effect, and as such the primary outcome of interest cannot be observed in the experimental sample due to the limited duration of experiments, which makes the estimation of ODR impossible. This paper is inspired to address this challenge by making use of an auxiliary sample to facilitate the estimation of ODR in the experimental sample. We propose an auGmented inverse propensity weighted Experimental and Auxiliary sample-based decision Rule (GEAR) by maximizing the augmented inverse propensity weighted value estimator over a class of decision rules using the experimental sample, with the primary outcome being imputed based on the auxiliary sample. The asymptotic properties of the proposed GEAR estimators and their associated value estimators are established. Simulation studies are conducted to demonstrate its empirical validity with a real AIDS application.

We consider the optimal decision-making problem in a primary sample of interest with multiple auxiliary sources available. The outcome of interest is limited in the sense that it is only observed in the primary sample. In reality, such multiple data sources may belong to different populations and thus cannot be combined directly. This paper proposes a novel calibrated optimal decision rule (CODR) to address the limited outcome, by leveraging the shared pattern in multiple data sources. Under a mild and testable assumption that the conditional means of intermediate outcomes in different samples are equal given baseline covariates and the treatment information, we can show that the calibrated mean outcome of interest under the CODR is unbiased and more efficient than using the primary sample solely. Extensive experiments on simulated datasets demonstrate empirical validity and improvement of the proposed CODR, followed by a real application on the MIMIC-III as the primary sample with auxiliary data from eICU.

With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer. To utilize the memory buffer more efficiently, we propose to keep more auxiliary low-fidelity exemplar samples rather than the original real high-fidelity exemplar samples. Such memory-efficient exemplar preserving scheme make the old-class knowledge transfer more effective. However, the low-fidelity exemplar samples are often distributed in a different domain away from that of the original exemplar samples, that is, a domain shift. To alleviate this problem, we propose a duplet learning scheme that seeks to construct domain-compatible feature extractors and classifiers, which greatly narrows down the above domain gap. As a result, these low-fidelity auxiliary exemplar samples have the ability to moderately replace the original exemplar samples with a lower memory cost. In addition, we present a robust classifier adaptation scheme, which further refines the biased classifier (learned with the samples containing distillation label knowledge about old classes) with the help of the samples of pure true class labels. Experimental results demonstrate the effectiveness of this work against the state-of-the-art approaches. We will release the code, baselines, and training statistics for all models to facilitate future research.

Transferring knowledge from large source datasets is an effective way to fine-tune the deep neural networks of the target task with a small sample size. A great number of algorithms have been proposed to facilitate deep transfer learning, and these techniques could be generally categorized into two groups - Regularized Learning of the target task using models that have been pre-trained from source datasets, and Multitask Learning with both source and target datasets to train a shared backbone neural network. In this work, we aim to improve the multitask paradigm for deep transfer learning via Cross-domain Mixup (XMixup). While the existing multitask learning algorithms need to run backpropagation over both the source and target datasets and usually consume a higher gradient complexity, XMixup transfers the knowledge from source to target tasks more efficiently: for every class of the target task, XMixup selects the auxiliary samples from the source dataset and augments training samples via the simple mixup strategy. We evaluate XMixup over six real world transfer learning datasets. Experiment results show that XMixup improves the accuracy by 1.9% on average. Compared with other state-of-the-art transfer learning approaches, XMixup costs much less training time while still obtains higher accuracy.