Efficient Data Selection

We resolve the threshold part of Question 4 of the COLT 2025 open problem "Data Selection for Regression Tasks" of Hanneke, Moran, Shlimovich and Yehudayoff. In vector-valued linear regression with square loss $\ell_{(x,y)}(W)=|Wx-y|_2^2$, where $x\in\mathbb{R}^d$, $y\in\mathbb{R}^m$ and the learner is the empirical risk minimizer of minimal Frobenius norm, we prove that the minimal budget of weighted examples that recovers the full-data loss on every finite dataset is exactly $n^*(d,m)=(m+1)d$. We further determine two more values of the weighted selection profile $F_w(d,m,n)$: at the near-threshold budget, $F_w(d,m,(m+1)d-1)=1+\frac{1}{dm^2}$, and at the spanning budget, $F_w(d,m,d)=d+1$ for every $m$, while $F_w(d,m,n)=\infty$ for $n<d$. For the smallest open intermediate cell $(d,m)=(2,2)$ we prove $F_w(2,2,3)\in[13/8,15/8]$ and $F_w(2,2,4)\in[5/4,3/2]$, reduce the conjectured exact values $13/8$ and $5/4$ to a finite moment problem on the circle with at most seven atoms, and establish strong structural evidence for the conjecture. The upper-bound techniques (a fixed-basis conic compression lemma, a determinant-facet rigidity theorem for maximal certificates, and sharp sparsification lemmas for zero-mean weighted point systems) are of independent interest. As a byproduct we correct an erroneous claim circulating in a recent unrefereed preprint, exhibiting an explicit dataset with $m=2$ on which no weighted selection of $2d$ points recovers the optimal loss. All results are new only for $m\ge 2$; the scalar case $m=1$ is due to Hanneke et al.

Modern systems are increasingly expected to transfer across tasks not specified during training. What data facilitates generalization in these new, unanticipated settings? One hypothesis is that data with more structural information could contain shared circuits and subprograms that could be recycled in a wider array of downstream settings. Epiplexity, a recently proposed measure of the structural information a compute-bounded learner can extract from data, provides a mechanism to reason about this relationship. In this paper, we show how to operationalize epiplexity as an online training signal for data selection and synthetic data generation. For selection, we fit scaling laws to the training loss curves of natural data domains to predict the expected epiplexity gain as a function of training tokens, and use this signal to adaptively determine the sampling weights over domains during training. For synthetic data generation, we define a generator's reward as the change in learner epiplexity over a buffer of previously generated data and use REINFORCE policy gradients to guide the generator toward an epiplexity-maximizing distribution. In both cases, higher epiplexity predicts improved downstream performance on zero-shot and fine-tuning based tasks, supporting the hypothesis that data rich in structural information yield representations that transfer across domains.

Although existing instruction data selection methods have introduced various metrics, the inherent complexity of real-world datasets makes it impractical for any single metric to generalize across all scenarios. Developers are thus often forced to manually inspect data and craft heuristic rules for each new application---a tedious and error-prone process. In this paper, we propose a paradigm shift from manual configuration to automated orchestration via the Instruction Data Selection Agent (DataMaster), which interprets user intent and autonomously composes optimal selection strategies. By allowing users to specify data needs through natural language descriptions, DataMaster simplifies data curation and removes the burden of manual strategy design. Extensive experiments across the math, medical, and code domains show that DataMaster outperforms static baselines in most settings and surpasses full-pool training in a substantial number of cases. The implementation of DataMaster and the scripts needed to reproduce the reported pipeline are publicly available at https://github.com/nju-websoft/DataMaster.

Procuring supervised fine-tuning (SFT) data forces a buyer to decide, before any downstream training, whether a candidate corpus is worth acquiring. We present \sys{}, a statistics-first gating architecture that treats procurement as a cost-aware routing problem over three intrinsic quality axes -- diversity, utility, and redundancy. Cheap blind measurements are summarised into per-axis estimates with confidence intervals; a gate accepts a decision only when intervals are tight, sample sizes are adequate, and the axes agree, otherwise it escalates the case to an adjudicative debate between a buy-advocate and a reject-advocate judge, resolved by a presiding verdict. On a controlled benchmark of 12 datasets ($2{\times}3{\times}2$ grid over the three axes) with 5 seeds, the gate reaches 0.90 accuracy and 0.83 $F_1$ at $0.017 per unit, sitting between an always-verify baseline (0.75) and an oracle upper bound (0.98) while spending less than always-escalate ($0.020). We further report honest negative diagnostics of the debate path: a con-side win rate of 0.80 ($p\approx3{\times}10^{-6}$) and a 52% position-flip rate under advocate swapping expose negativity and positional biases that a naive LLM-judge would hide. We frame the injected-knob evaluation explicitly as a controlled synthetic benchmark for measurement fidelity and routing calibration, and delimit external validity as future work.

Small-scale language models (SLMs) are attractive for retrieval-augmented generation (RAG) in resource-constrained settings, but their limited capacity makes them highly sensitive to noisy or spurious retrieved evidence. Existing preference-based methods such as RoseRAG select only the hardest single preference pair via hard argmin/argmax, discarding the remaining signal; others treat multiple pairs as independent binary comparisons, resulting in low data utilization. We propose RIMS, a three-stage preference optimization framework comprising (1) synthetic chain-of-thought preference data generation via rejection sampling using the target SLM itself without relying on proprietary models, (2) a differentiable soft aggregation mechanism that replaces hard selection with a smooth operator, preserving gradient signal from all preference pairs while retaining the discriminative structure of margin-aware selection, and (3) preference optimization with the smoothed objective applied to multiple alignment algorithms. We theoretically show that the smoothed approximation admits a controllable error bound and that smooth aggregation yields provably tighter gradient alignment to the oracle objective than hard selection. Experiments on four multi-hop question answering benchmarks show that our approach outperforms state-of-the-art baselines across multiple SLM backbones, achieving consistent gains in Exact Match and F1 under noisy retrieval conditions. Our implementation is available at https://github.com/tptrix29/RIMS.

Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning. This separation is incomplete: when examples are scored and kept online during fine-tuning, the choice of which data to train on already changes the model's behavioral preferences. We study online data selection as an implicit alignment mechanism. Given the same base model, optimizer, and selected-token budget, we compare random, loss-based, quality-based, and diversity-based online selectors and measure the behavioral drift they induce without any preference optimization. The proposed evaluation tracks helpfulness, refusal rate, verbosity, truthfulness, sycophancy, calibration, and jailbreak robustness, together with diagnostics for which behavioral modes are over-represented in the selected data. We formalize online selection as a reweighted SFT objective whose weights define an implicit preference over response styles and safety postures, so that an online scorer plays the role usually assigned to a reward model. This view predicts that high-scoring data can systematically favor longer, more assertive, more compliant, or more refusal-prone behaviors depending on how the online score is defined. Empirically, selectors that are statistically indistinguishable in task accuracy diverge sharply in refusal rate, verbosity, and sycophancy, and we show that the direction of the shift is predictable from the attribute mixture of the selected data. We introduce Alignment Drift Auditing (ADA), a controlled protocol for quantifying selection-induced behavioral movement, and Alignment-Aware Selection (AAS), a diagnostic online selector that retains data efficiency while constraining drift along safety and style axes.

Vision-Language-Action (VLA) models are typically trained by imitation learning on large-scale robot demonstration datasets, but more data does not necessarily yield better policies due to redundancy, noise, and uneven coverage. Existing data selection methods often assess demonstrations at either the trajectory or state-action level, missing the reusable structures that compose long-horizon behaviors. In this paper, we propose SIEVE, a structure-aware data selection method for VLA imitation learning. SIEVE views demonstrations as compositions of reusable primitives and transition interfaces. It first discovers visuo-motor primitives from segmented trajectories, then allocates selection budgets to composition patterns by maximizing reuse-aware structural exposure under diminishing returns. Finally, it selects medoid trajectories within each composition-pattern bucket to retain central, stable, and imitation-friendly demonstrations. Experiments across multiple datasets, benchmarks, and VLA models show that SIEVE consistently outperforms competitive data selection baselines. Notably, SIEVE can surpass full-data training while using only 50% of demonstrations and 50% of training steps, suggesting that reusable structure, captured through primitives and transitions, is an important signal for efficient VLA imitation learning.

Selecting a small, diverse, high-quality subset from a massive pool of candidates is a recurring primitive in modern machine learning -- data curation and coreset selection for training and fine-tuning large models, active-learning batch acquisition, prompt and exemplar selection for in-context learning, retrieval diversification, and experimental design. Determinantal Point Processes (\DPP s) give a principled, well-calibrated notion of diversity for this task, but their \emph{MAP} objective -- pick a size-$k$ subset $S$ maximizing $\logdet(L_S)$ -- is NP-hard, and the standard greedy and sampling algorithms scale superlinearly in the ground-set size $n$. This cost is prohibitive precisely in the data-centric regime where diversity matters most, where $n$ ranges over millions to billions of candidate examples, features, or embeddings. We recast \DPP-MAP as a continuous optimization problem over the Stiefel manifold, and show that its first-order optimality conditions form a \emph{Nonlinear Eigenvalue Problem with eigenvector dependency} (\NEPv) of a previously unstudied form. This \NEPv\ admits a self-consistent field (\SCF) iteration with a spectral-gap-based local contraction guarantee, giving a principled iterative solver where the diversity objective drives an eigenvector-dependent operator. The resulting algorithm, \OurMethod, requires only matrix-vector products with the kernel and runs in time $O\!\big((ndk+nk^2)\,t\big)$ for a small number of iterations $t$, scaling near-linearly in $n$ and integrating directly with low-rank and feature-map kernels common in ML. This paper focuses on the relaxation, solver, and scaling analysis; full real-data benchmarking is left to a planned empirical study.

As Large Language Model (LLM) datasets scale to trillions of tokens, data selection has emerged as a critical frontier to filter out uninformative noise and construct adaptive learning trajectories. Beyond static heuristic filtering, advanced data selection methods for LLM training largely follow two paradigms, each with fundamental limitations. Influence-based methods provide principled bi-level objectives but require intractable inverse-Hessian computations, while excess-loss methods are computationally efficient but rely on a static reference model that becomes misaligned with the evolving proxy model during training. We propose BLADE (Bi-Level Adaptive Data sElection), a Hessian-free framework for data selection. BLADE reformulates the bi-level optimization problem underlying influence-based methods as a penalized single-level objective via Lagrange multipliers, avoiding inverse-Hessian computation while revealing a principled connection to excess-loss based data selection. The resulting objective recovers an excess-loss form but replaces the static reference model with a dynamic one that stays synchronized with training. Theoretically, we prove that this penalized formulation guarantees first-order convergence. For efficient online batch selection, we instantiate BLADE as a memoryless randomized block-coordinate Frank-Wolfe algorithm. Extensive experiments show that BLADE consistently outperforms state-of-the-art data selection baselines, providing a practical recipe for LLM training.

Data acquisition is a major bottleneck for learning in real-time streams: analysts must decide on the fly which labels to purchase while respecting a rolling budget. However, existing online active learning rarely unifies pricing, information gain, and rolling budget constraints under concept drift. We introduce QueryMarket, a market-inspired framework that queries each incoming data point based on its estimated utility to the model and its price. Within this framework, we propose OVBAL (online variance-based active learning), which integrates data pricing with information-driven selection by estimating each sample's marginal utility via a D-optimality criterion with exponential forgetting and executing cost-aware purchases under rolling budget constraints. OVBAL yields a simple, fully online decision rule that adapts to nonstationary streams and heterogeneous label costs. Experiments on synthetic data and a real-world solar power generation forecasting task show that OVBAL is particularly effective under seller-centric pricing and yields a more favorable long-run error-cost trade-off in the real-world task under both pricing schemes.

Diversity plays a critical role in data selection, improving performance under fixed data budgets by reducing redundancy and repetition. However, optimizing for diversity is inherently challenging, as it is a set-level property that depends on interactions between data points rather than individual examples. As a result, existing approaches typically rely on proxies or approximations, which often fail to ensure sufficiently diverse subsets. In this work, we directly optimize diversity by introducing a probabilistic diversification framework based on the G-Vendi score, optimized via exponentiated gradient descent. Our method produces subsets that are substantially more diverse than those obtained via random sampling, achieving a +489 increase in G-Vendi score on a 500k-sample subset. We evaluate our approach on FineWeb and DCLM, where it consistently outperforms existing methods. Notably, SPOKES (diversity-only) improves average downstream performance by +0.4 and +0.5 points over random sampling on DCLM and FineWeb, respectively. More importantly, jointly optimizing for both quality and diversity yields the strongest results: SPOKES achieves gains of +1.5 and +1.4 points on DCLM and FineWeb, outperforming all baselines, including semantic deduplication and quality filtering.

Dynamic data pruning techniques aim to reduce computational cost while minimizing information loss by periodically selecting representative subsets of input data during model training. However, existing methods often struggle to maintain strong worst-group accuracy, particularly at high pruning rates, across balanced and imbalanced datasets. To address this challenge, we propose RCAP, a Robust, Class-Aware, Probabilistic dynamic dataset pruning algorithm for classification tasks. RCAP applies a closed-form solution to estimate the fraction of samples to be included in the training subset for each individual class. This fraction is adaptively adjusted in every epoch using class-wise aggregated loss. Thereafter, it employs an adaptive sampling strategy that prioritizes samples having high loss for populating the class-wise subsets. We evaluate RCAP on six diverse datasets ranging from class-balanced to highly imbalanced using five distinct models across three training paradigms: training from scratch, transfer learning, and fine-tuning. Our approach consistently outperforms state-of-the-art dataset pruning methods, achieving superior worst-group accuracy at all pruning rates. Remarkably, with only $10\%$ data, RCAP delivers $>1\%$ improvement in performance on class-imbalanced datasets compared to full data training while providing an average $8.69\times$ speedup. The code can be accessed at https://github.com/atif-hassan/RCAP-dynamic-dataset-pruning

The performance of modern language models depends critically on pretraining data composition. Yet existing data selection methods rely on auxiliary classifiers for document scoring or mixture optimization, adding computational overhead and dependence on labeled data. We propose WebGraphMix, a lightweight data selection framework that computes structural centrality scores over the Common Crawl host-level web graph and uses them to vary the proportion of central versus peripheral documents in the pretraining mixture. We hypothesize that central hosts expose models to reusable abstractions, while peripheral hosts encode specialized, long-tail knowledge. WebGraphMix computes centrality scores efficiently at web scale, requiring no model training, labeled data, or downstream supervision. We integrate WebGraphMix into the DataComp-LM pipeline and train models at 400M and 1B parameter scales with 8B and 28B tokens respectively, evaluating on 23 tasks ranging from factual knowledge to symbolic reasoning. Our experiments show that central and peripheral web regions encode complementary capabilities. Mixture combining both at a ratio of 1:1 achieves 41.4% on average, compared to 39.8% for uniform sampling. Combining structural scores with document-level quality classifier scores further improves performance to 43.8%. These findings demonstrate that web graph topology is a meaningful axis for pretraining data curation, capturing information that is largely orthogonal to existing content-based approaches.

Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large language models (LLMs), yet efficiency is often studied through isolated techniques rather than as an interacting system of limits. This survey adopts a constraint-centric perspective and organizes recent progress around three coupled bottlenecks: data efficiency (what to train on), memory efficiency (how to fit training), and compute budget awareness (when and where to spend FLOPs). On the data axis, we review selection and pruning methods that maximize learning per token, ranging from scalable proxy signals based on learning dynamics to gradient- and influence-based scoring, as well as difficulty-aware and curriculum-style strategies. We highlight emerging evidence that different notions of good data dominate in different regimes, implying that optimal subsets depend on the task objective and resource budget rather than being universal. On the systems side, we show that GPU memory, not raw compute, is often the dominant bottleneck in fine-tuning, and that effective scaling requires jointly reducing weight storage, optimizer states, and activation memory rather than optimizing any single component in isolation. Beyond memory, we frame training and inference as compute-governed processes in which optimization, data selection, and decoding must explicitly account for finite FLOP budgets. We review evidence for compute-optimal allocation and stopping rules, where computation should be halted or reallocated once marginal performance gains fall below a budget-dependent threshold. Together, these results unify compute-aware data selection, scaling laws, and adaptive inference under a common principle of resource-conditioned decision-making.

Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains. Existing methods either select samples independently within each domain or rely on computationally expensive proxy models to learn continuous domain weights. We propose PartitionSel, a cross-domain minibatch selection approach that maximizes a validation-guided gradient-matching utility under per-domain budgets encoded as a partition-matroid constraint. By coupling the per-domain budgets through a single utility, PartitionSel is designed to reduce redundancy in selections across domains. The proposed objective is weakly submodular and admits an orthogonal matching pursuit algorithm with provable approximation guarantees. Empirically, we evaluate PartitionSel for minibatch selection during the fine-tuning of Qwen2.5 and Llama-3 on MetaMathQA and Mol-Instructions. PartitionSel achieves robust gains over per-domain and domain-agnostic baselines on both benchmarks. It also reduces the number of conflicting gradient pairs within each batch, indicating that the cross-domain coupling translates into more compatible training updates.

Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models. Train-free selectors are scalable but rely on proxies such as embedding similarity or clustering, which may not match the target objective. Train-based selectors better reflect downstream utility through gradient signals, subset evaluation, or Shapley attribution, but require many costly train--evaluate iterations. We propose Hierarchical Active Region Pruning (HARP), an efficient train-based selector that preserves downstream alignment while reducing selection cost. HARP organizes the training pool into a node--leaf hierarchy, evaluates only representative leaves, and infers unmeasured utilities with empirical Bayes posteriors. It then selects data using two complementary envelopes: HARP-C, which conservatively controls redundancy, and HARP-E, which additively rewards complementary regions. We theoretically show that, under local smoothness and bounded estimation error, HARP controls selection error while reducing train--evaluate cost. We further validate that HARP variants achieve the best result and outperform the strongest baseline by up to $+8.9$ points, while using roughly $7\times$ fewer training examples.

Database vendors recently released AI functions that can be used in filter predicates. As such functions often rely on costly, black-box ML models, they unveil new data management challenges. Concretely, traditional data skipping techniques for integer and string data fail to be applicable to the new filter type. Indeed, there is no known mechanism for pruning non-qualifying row groups, e.g., when reading files from blob storage. In this work, we initiate the study of data skipping techniques for ML filters. We make the case that Parquet's default min-max metadata is enough to enable pruning. To this end, we draw connections to two lines of research: (i) the recently proposed query language for ML models and (ii) neural network verification. Our preliminary results on ReLU architectures show that on tables from TPC-H and TPC-DS, the average pruning effectiveness for filters of selectivity below 0.1% amounts to 27.4%. Finally, inspired by research on spatial joins, we propose an enhanced metadata structure: a size-bounded 2D convex hull that verification tools can make better use of, increasing the pruning effectiveness to 38.31%, while occupying at most 45 bytes per row group and column pair. We observe an end-to-end speedup of 1.07$\times$ over PyTorch in DuckDB.

Synthetic data are increasingly used to train neural networks, yet distributional mismatch with real data limits their effectiveness when used indiscriminately. A common strategy is to learn data weights via bi-level optimization, which we refer to as Meta-learning for Training-data Selection (MTS). Interestingly, in practice, MTS often performs below expectation. We identify two obstacles in properly training MTS: a poor gradient signal-to-noise ratio (GSNR), which causes optimization difficulties, and lack of informative features that correlates with data quality. We present a mathematical analysis of MTS, which reveals the dynamics of normalized data weights and the relation between disparate data quality and poor GSNR. The analysis suggests a a simple yet effective solution: increasing the batch size. Further, we propose a set of informative features that capture the positions of training data in their distributions and training dynamics. Experiments across four benchmarks show consistent improvements, achieving average gains of 5.49% over training without selection and 2.89% over the strongest baseline.

The annealing phase is a pivotal convergence stage in LLM pre-training that ultimately determines final model quality. However, effectively selecting training data during this phase remains a key challenge. Current strategies rely on empirical heuristics, such as domain filtering or context extension, which lack a principled grounding in optimization theory. In this work, we characterize the annealing phase through the lens of the loss landscape's spectral geometry. We argue that optimal convergence requires gradient updates to satisfy heterogeneous constraints across different eigen-directions. Building on this insight, we formulate data selection as a problem of satisfying these directional constraints. To this end, we propose DiReCT (Directionally-Restrained Constrained Training), a novel framework that reformulates sample selection in the annealing stage as a constrained optimization problem. By imposing explicit directional constraints on per-sample gradients based on the spectral properties of the Hessian, DiReCT identifies samples that align with the optimal curvature-aware descent path. Extensive experiments across various model scales demonstrate that DiReCT consistently achieves state-of-the-art performance. For future research, code is available at https://github.com/xuyj233/Direct.

Adaptive sensing strategies that selectively sample data are increasingly used in wearable health systems to improve prediction performance under limited data budgets, yet their benefits across individuals remain poorly understood. Here, we evaluate adaptive selection of time windows for model training under fixed measurement budgets across multiple sensing modalities, including heart rate, activity, and ecological momentary assessment (EMA), in a longitudinal wearable dataset. We quantify performance gains relative to random sampling using both area under the receiver operating characteristic curve (AUROC) and F1 score. Adaptive strategies yield substantial improvements in AUROC for participants with low baseline performance (with gains up to 0.7), while offering limited or negative gains for participants with strong baselines. Across modalities, adaptive gain is strongly inversely correlated with baseline performance (Pearson r = -0.67; Spearman p = -0.62). At the participant level, most individuals benefit in AUROC (60-80% across modalities), although improvements in F1 are smaller and less consistent. These findings show that adaptive sensing is not uniformly beneficial, but instead provides the greatest value in underperforming settings. Our results support selective deployment strategies that tailor adaptive sensing based on baseline performance to improve efficiency in wearable health monitoring.

Mid-training has become an important stage in modern LLM development, using large-scale curated mixtures to strengthen capabilities before final post-training. Its data selection problem is distinct: the data are optimized under a pretraining-style objective at near-pretraining scale, but are curated toward downstream capabilities and drawn from heterogeneous sources with different formats and training roles. As a result, effective selection requires both scalability and source-adaptive semantic criteria. Existing model-based methods scale well, but provide only implicit quality signals. Semantic selection methods offer stronger judgments, but usually assume fixed rubrics or standardized data formats. To address this mismatch, we propose MIRA, a source-aware filtering framework based on self-anchored rubric discovery. The key idea is to make rubric construction part of data selection: MIRA first discovers what should be evaluated for each source group, then distills those judgments into scalable student scorers for full-corpus filtering. On code-oriented mid-training with 21 sources and 5 source groups, MIRA outperforms selection baselines across nine code benchmarks and matches the full-corpus run while using only half the tokens.

Submodular optimization has become a fundamental paradigm for data selection, retrieval, summarization, and representation learning due to its ability to model coverage, diversity, and representativeness. However, classical submodular objectives optimize only the selected subset and do not explicitly preserve structural information between the selected subset and the remaining data. In many modern machine learning applications, including train/validation/test splitting, benchmark construction, and robust subset selection, the quality of a selection depends critically on preserving balanced structure across both the selected subset and its complement. In this work, we introduce Complement Submodular Information (CSI), a new class of complement-aware submodular objectives that quantify shared structural information between a subset and its complement. Our framework induces complement-aware variants of several classical submodular functions including Facility Location, Graph Cut, LogDet, Saturated Coverage, Set Cover, Probabilistic Set Cover, and Feature Based Functions. We analyze the theoretical properties of CSI objectives and show that they exhibit approximate monotonicity under bounded curvature conditions, leading to near-$(1-1/e)$ greedy approximation guarantees. Empirically, CSI objectives consistently outperform standard submodular objectives on robust hidden-slice-aware subset selection. In particular, CSI objectives significantly improve preservation of coherent rare/tail semantic structure while simultaneously suppressing noisy and isolated outliers, leading to substantially improved downstream predictive performance. Synthetic experiments further illustrate how different CSI instantiations capture complementary notions of representativeness, diversity, connectivity, and balanced neighborhood preservation.

As LLMs continue to scale up, improving training efficiency heavily relies on effective data utilization. Data selection mitigates this issue by allocating the limited training budget to high-value examples that optimally facilitate the model's target behavior. Most existing approaches define target behavior via a set of target examples and score candidate training data based on their estimated influence on these samples. However, such methods uniformly treat all target examples as equally important, ignoring the varying relevance of individual examples to model optimization. Specifically, target examples that align closely with the model's inherent behavior deliver stronger supervisory signals, whereas discrepant examples yield only weak and ineffective local guidance. We propose PRISM, a Preference-aware Influence function based Data Selection Method. It leverages model preference to assign weights to target examples and builds a preference-aware target direction. PRISM evaluates candidate training samples according to their influence on this direction, and prioritizes data budget allocation to samples that effectively drive the model to match expected target behavior. Theoretical analysis verifies that weighted preference construction generates a superior first-order gradient direction for boosting target preference, compared with uniform aggregation strategies. Extensive experiments covering diverse model architectures and parameter scales demonstrate that PRISM achieves better performance in efficient fine-tuning and safety-aligned supervised fine-tuning rectification. The results validate that accurate characterization of target behavior serves as the core of cost-effective data selection.

Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data selection and parameter-efficient fine-tuning as isolated processes, our empirical analysis suggests they may be intrinsically coupled. We posit the Strong Map Hypothesis: a sparse subset of attention heads plays a dominant role in task-specific adaptation, acting as keys that unlock specific data patterns. Building on this observation, we propose From Parameters to Data (P2D), a unified framework that leverages these task-sensitive attention heads as a dual compass for both sample mining and structural pruning. To rigorously quantify the total pipeline cost, we introduce the Alignment Efficiency Ratio (AER) metric for both selection latency and training time. Mechanistically, P2D identifies critical heads via a lightweight proxy and uses them as a functional filter to curate high-affinity data, establishing a synergistic pipeline. Empirically, by updating merely 10% of attention heads on 10% of the data, P2D achieves an 8.3 pp performance gain over strong baselines and delivers a 7.0x end-to-end time speedup. These results validate that precise parameter-data synchronization eliminates redundancy, offering a new paradigm for efficient alignment.

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal protection against such leakage, yet DP fine-tuning of LLMs still suffers from substantial utility degradation due to gradient clipping and noise injection. Existing work improves this trade-off by combining DP with parameter-efficient fine-tuning methods such as LoRA, which constrain the form of updates. In this work, we study a complementary direction: selective fine-tuning, which constrains where updates are applied. We propose DP-SelFT, a framework for differentially private selective fine-tuning of LLMs. DP-SelFT addresses three DP-specific challenges in parameter selection: avoiding repeated privacy cost, improving stability under noisy estimates, and selecting parameters that remain useful under clipped and noisy updates. It first constructs a lightweight DP synthetic dataset and performs selection only on this synthetic data, so the selection stage incurs no additional privacy cost. It then conducts layer-level selection by temporarily training candidate layer subsets on a synthetic training split and evaluating them on a synthetic validation split. Crucially, this temporary training is performed under a perturbation regime matched to downstream DP fine-tuning, with worst-case perturbations of the same scale as DP noise. This favors layer subsets that are not only learnable but also robust to noisy private updates. Experiments on benchmark tasks show that DP-SelFT consistently improves the privacy--utility trade-off over existing DP fine-tuning baselines under the same privacy guarantees.

Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this problem as a Weighted Independent Set (WIS) on a similarity graph, where nodes represent data samples weighted by influence, and edges connect semantically redundant pairs. This formulation naturally yields subsets that are simultaneously high-quality and diverse. However, two challenges arise in practice: naive node weights fail to distinguish informative signals from gradient noise, and edge construction under heterogeneous domain distributions produces structurally imbalanced graphs that bias selection toward sparse regions. To address these issues, we introduce two principled refinements from a unified graph perspective: (1) \textit{node value calibration} that restricts influence estimation to the bilateral salient subspace to ground node importance in task-relevant signals rather than surface-level statistics; (2) \textit{local scale normalization} that adapts edge thresholds to local neighborhood density, mitigating graph imbalance induced by cross-domain distribution shifts. Together, these components yield a robust and scalable data selection pipeline dubbed SEED. We further construct \texttt{Honeybee-Remake-SEED-200K}, a compact multimodal dataset curated by SEED. Extensive experiments show that SEED consistently outperforms state-of-the-art methods on instruction tuning, visual instruction tuning, and semantic segmentation across diverse model families.

Influence functions approximate how removing a training example changes a quantity of interest, called the target function, such as a held-out loss. To estimate the influence of a group of examples, the standard practice is to sum the individual influences of its members. However, this sum does not capture how examples jointly affect the target: a pair of examples may be redundant or complementary, but the sum cannot distinguish these cases. We propose an interaction-aware influence function that characterizes how interactions between examples influence the target. By expanding the target to second order around the trained parameters, we obtain an estimator that augments the standard sum with a pairwise interaction term that captures the alignment between two examples' effects on the target. We empirically evaluate our estimator in two settings. First, on six dataset-model pairs spanning logistic regression, MLPs, and ResNet-9, our estimator tracks leave-group-out retraining substantially better than first-order influence across all settings. Second, when used as a greedy selection rule for instruction-tuning data on Llama-3.1-8B, it beats prior influence-based and representation-similarity baselines on five of seven downstream tasks, in a regime where standard influence-based selection underperforms random selection.

Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly focus on designing sample-importance criteria, i.e., deciding what to select, while typically fixing the selected data volume as the target ratio throughout training. Thus, they are often dynamic in sample identity but static in data volume. In this work, we revisit data selection from an optimization perspective and show that selected-data training induces an implicit regularization effect modulated by the instantaneous selection ratio. This reveals a key trade-off: lower ratios amplify selection-induced regularization, whereas higher ratios preserve data coverage and optimization fidelity. Motivated by this insight, we propose PODS, a Plug-and-play Oscillatory Data-volume Scheduling framework. Rather than introducing another sample-scoring metric, PODS serves as a lightweight module that dynamically schedules how much data to select over training. Under the target selection ratio, PODS alternates between low-ratio regularization phases and high-ratio recovery phases to exploit selection-induced regularization without sacrificing optimization stability. With its lightweight, ratio-level, and task-agnostic design, PODS is compatible with existing static and dynamic selection methods and broadly applicable across training paradigms. Experiments across various datasets, architectures, and tasks show that PODS consistently improves the efficiency-generalization trade-off, e.g., reducing ImageNet-1k training cost by 50% with improved accuracy and accelerating LLM instruction tuning by over 2x without performance degradation.

Learning-assisted algorithm design often has to make reliable search decisions under small evaluation budgets, where committing to a single metaheuristic can be unreliable. We propose WASHH, a Whale-guided Adaptive Selection Hyper-Heuristic for continuous black-box optimization. WASHH uses WOA as the main exploitation backbone, but treats PSO-style memory, GWO-style leader averaging, DE-style variation, local coordinate search, and anchor-guided refinement as selectable search behaviors. An online reward controller allocates evaluations according to observed improvements, while anchor refinement exploits inexpensive reference configurations such as box centers or default model settings without bypassing black-box evaluation. On ten 30-dimensional benchmark functions with 10 independent runs and 12,000 evaluations, WASHH achieves the best average rank, 1.10, and is best or tied best on all ten functions. It strictly improves over WOA on eight functions and ties WOA at the numerical optimum on Rastrigin and Griewank. We further study SVC hyperparameter configuration for breast cancer diagnosis under a 300-evaluation budget. WASHH obtains the lowest mean validation log loss among the compared optimizers, suggesting that anchor-aware selection hyper-heuristics are a practical lightweight direction for LEAD systems.

Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying useful data and efficiently fine-tuning. High-quality and diverse pruned data can help models achieve lossless performance at a lower cost. In this paper, we propose \textbf{SLAP}, a novel batch-aware data selection framework that evaluates the learnability of entire batch compositions rather than individual. SLAP ensures comprehensive data distribution coverage through distribution-aware stratified sampling while maximizing intra-batch diversity through relative distance optimization. By leveraging Hessian-approximated gradient information for dynamic batch selection, SLAP significantly outperforms existing state-of-the-art methods across multiple model architectures (LLaMA, ChatGLM) and diverse downstream tasks including multi-turn dialogue, multilingual translation, and question answering. Most notably, SLAP achieves superior performance with 20-40% less training data compared to full dataset training, substantially reducing computational costs while maintaining or improving model capabilities. These results establish SLAP as a powerful approach for efficient and effective instruction tuning of large language models.

Data selection during supervised fine-tuning (SFT) can critically change the behavior of large language models (LLMs). Although existing work has studied the effect of selecting data based on heuristics such as perplexity, difficulty, or length, the reported findings are often inconsistent or context-dependent. In this work, we systematically study the role of data difficulty in fine-tuning from both empirical and theoretical perspectives, and find that there is no universally optimal difficulty level; rather, its effectiveness depends on the dataset size. We show that for a fixed data budget, there exists an optimal data difficulty for SFT, and that this optimal difficulty shifts toward harder data as the data budget increases. To explain this phenomenon, we conduct controlled synthetic experiments that reveal a simple underlying mechanism: the interplay between the (in-distribution) generalization gap and the extrapolation gap. We further support this mechanism through a theoretical analysis using PAC-Bayesian generalization bounds. Overall, our results clarify how data size and difficulty jointly affect the trade-off between generalization and extrapolation in SFT, providing guidance for difficulty-based data selection under certain model and data conditions.

Attributing model behavior to training data is an evolving research field. A common benchmark is data removal, which involves eliminating data instances with either low or high values, then assessing a model's performance trained on the modified dataset. Many existing studies leverage Shapley-based data values for this task. In this paper, we demonstrate that these data values are not optimally suited for pruning low-value data when only a limited amount of data remains. To address this limitation, we introduce the Constraint-Data-Value-Maximization (CDVM) approach, which effectively utilizes data attributions for pruning in low-data scenarios. By casting pruning as a constrained optimization that both maximizes total influence and penalizes excessive per-test contributions, CDVM delivers robust performance when only a small fraction of the data is retained. On the OpenDataVal benchmark, CDVM shows strong performance and competitive runtime.

As model families, training recipes, and compute budgets become increasingly standardized, further gains in machine learning systems depend increasingly on data. Yet data engineering remains largely manual and ad hoc: practitioners repeatedly search for external datasets, adapt them to existing pipelines, validate candidate data through downstream training, and carry forward lessons from prior attempts. We study task-conditioned autonomous data engineering, where an autonomous agent improves a fixed learning algorithm by optimizing only the data side, including external data discovery, data selection and composition, cleaning and transformation. The goal is to obtain a stronger downstream solution while leaving the learning algorithm unchanged. To address the open-ended search space, branch-dependent refinement, and delayed validation inherent in autonomous data engineering, we propose DataMaster, a data-agent framework that integrates tree-structured search, shared candidate data, and cumulative memory. DataMaster consists of three key components: a DataTree that organizes alternative data-engineering branches, a shared Data Pool that stores discovered external data sources for reuse, and a Global Memory that records node outcomes, artifacts, and reusable findings. Together, these components allow the agent to discover candidate data, construct executable training inputs, evaluate them through downstream feedback, and carry useful evidence across branches. We evaluate DataMaster on two types of benchmarks, MLE-Bench Lite and PostTrainBench. On MLE-Bench Lite, it improves medal rate by 32.27% over the initial score; on PostTrainBench, it surpasses the instruct model on GPQA (31.02% vs 30.35%).

Data selection studies the problem of identifying high-quality subsets of training data. While some existing works have considered selecting the subset of data with top-$m$ Data Shapley or other semivalues as they account for the interaction among every subset of data, other works argue that Data Shapley can sometimes perform ineffectively in practice and select subsets that are no better than random. This raises the questions: (I) Are there certain "Shapley-informative" settings where Data Shapley consistently works well? (II) Can we strategically utilize these settings to select high-quality subsets consistently and efficiently? In this paper, we propose a novel data selection framework, NASH (Non-linear Aggregation of SHapley-informative components), which (I) decomposes the target utility function (e.g., validation accuracy) into simpler, Shapley-informative component functions, and selects data by optimizing an objective that (II) aggregates these components non-linearly. We demonstrate that NASH substantially boosts the effectiveness of Shapley/semivalue-based data selection with minimal additional runtime cost.

Meta-learning for algorithm selection relies on a meta-dataset in which each row corresponds to a supervised learning dataset described by meta-features and labelled with a target value that is associated with algorithm choice (typically, some function of algorithm performance). A persistent limitation is that the number of curated real-world datasets is small, resulting in sparse meta-datasets that constrain meta-learner generalisation. In this paper, we address this problem by augmenting the meta-dataset with synthetic regression datasets produced via a large language model (LLM), with generation steered toward target regions of a low-dimensionality performance space. In our experiments, we adopt a two-dimensional geometric setting defined by the cross-validated $R^2$ scores of two anchor algorithms, known as landmarkers. We compare two augmentation strategies: (1) uniform sampling, which distributes synthetic datasets across the performance space; and (2) margin-based sampling, which concentrates them near the decision boundary where landmarker preference is most ambiguous. Across 42 real-world UCI regression datasets and 730 synthetic datasets, both strategies substantially improve meta-learner performance over the unaugmented baseline under regression and multi-label evaluation formulations. However, uniform augmentation consistently outperforms margin-based augmentation, achieving a 17.47% relative reduction in Hamming loss, a 100.41% relative improvement in subset accuracy, and a +6.09% relative gain in pooled out-of-fold $R^2$. These results lead us to postulate a central thesis: the performance of algorithms resides on a low-dimensional performance manifold, whose reconstruction bias may be minimised by user-guided LLMs that seek to maximise uniform $ε$-cover, and consequently, lead to improved meta-learning for algorithm selection.

Targeted data selection aims to identify training samples from a large candidate pool that improve performance on a specific downstream task. Many recent methods estimate candidate utility by aggregating local attribution scores along a trajectory induced by the candidate pool. When the pool is heterogeneous, however, this reference trajectory may be misaligned with the dynamics of a target-aligned selected subset, creating what we call reference path bias. We propose an alternative reference path: a validation-induced flow obtained from a short, capacity-limited warmup on the available target validation proxy. Along this path, candidates are scored by a normalized endpoint loss drop, yielding a simple zero-order selection rule that requires no candidate gradients or Hessian approximations. Across controlled logistic, vision, and instruction-tuning experiments, this score is competitive with strong dynamic attribution baselines while substantially reducing warmup and storage cost. Moreover, since the reference trajectory is decoupled from any specific candidate pool, the same compact warmup can be reused across additional pools without recomputing the trajectory.

Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty-aware data selection methods attempt to address this by prioritizing moderately difficult prompts, yet our analysis reveals three limitations: difficulty estimates become inaccurate under policy drift, data selection alone yields limited final-performance gains, and inference efficiency remains largely unchanged. These findings suggest that efficient and effective RL requires more than filtering by difficulty: the policy should learn to solve hard tasks while producing concise responses for easy ones. To this end, we propose Dare, a unified framework that co-evolves difficulty estimation with the policy via self-normalized importance sampling, maintains diverse difficulty coverage through a symmetric Beta sampling distribution, and applies tailored training strategies across difficulty tiers with adaptive compute allocation. Extensive experiments across multiple models and domains demonstrate that Dare consistently outperforms existing methods in training efficiency, final effectiveness, and inference efficiency, producing more concise responses on easy tasks while improving correctness on hard ones. Code is available at https://github.com/EtaYang10th/DARE.

Imitation learning for robotic tasks has relied primarily on policies trained only on successful demonstrations, although failures are unavoidable during human data collection. Many existing approaches for exploiting failure data require additional data processing or iterative policy updates through autonomous rollouts, making it difficult to directly and stably utilize failure data accumulated during data collection. In this work, we propose a method that learns latent representations of success-failure discrepancies and incorporates them into the attention mechanism. During inference, an appropriate latent mode is selected from the initial observation to improve action stability. Furthermore, we introduce a post-training metric that quantifies the attention discrepancy between each failure sample and successful demonstrations to select failure data. Simulation results show that the proposed method improves task success rates when trained with failure data and that the proposed metric identifies failure samples that are beneficial for learning when combined with successful demonstrations. These results suggest that the proposed method can support more efficient use of collected demonstrations in robotic data collection pipelines.

The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as LLM-as-a-Judge, have proven their effectiveness in addressing this but suffer from prohibitive computational costs and lack of interpretability. To bridge this gap, we propose One-Step-Train (OST), a framework that reformulates data selection as an incremental optimization utility ranking problem. Instead of relying on semantic heuristics, OST estimates the marginal utility of each sample via a simulated single-step update on a lightweight proxy. Experiments on the Qwen series across multimodal mathematical reasoning benchmarks demonstrate that OST achieves Pareto-optimal efficiency. By selecting the top-50 subset, OST reduces training costs by 43% (and total time consumption by 17) while surpassing the strong LLM-as-a-Judge baseline by 1.8 points. Furthermore, under a fixed compute budget, our method using only the top-20 subset achieves a 5.6 point gain over LLM-as-a-Judge, improves upon heuristic scoring baselines like DEITA, and outperforms the Full-SFT baseline by 8.8 points. Notably, while Full-SFT suffers from performance degradation due to noise, our optimization-grounded approach effectively identifies toxic samples, successfully reversing the negative transfer frequently observed in complex reasoning tasks.

Data selection methods address a critical challenge in LLM post-training: effectively leveraging scarce, high-fidelity target data alongside abundant but imperfectly aligned general training data. In this work, we move beyond the data-selection framing and introduce Dr. Post-Training (Data-Regularized Post-Training), a novel framework that reconceptualizes general training data as a data-induced regularizer that prevents overfitting to the scarce target objective, rather than serving as a pool for selection. Specifically, our framework proposes that at each training step, construct a feasible set of model update directions using the general training data, and project the model update direction specified by the scarce target data onto that feasible set. Standard training and existing data selection methods arise as special cases with different choices of the data-induced regularizer, and these methods correspond to different points on a bias--variance spectrum with different regularization strength. Building on this view, we propose a family of methods offering a richer design space and more flexible bias--variance tradeoffs. For practical LLM-scale use, we introduce careful system optimizations that realize these methods with minimal overhead. Extensive experiments across SFT, RLHF, and RLVR show that our methods consistently outperform state-of-the-art data selection baselines, and system benchmarks confirm their efficiency.

In Large Language Model (LLM) fine-tuning, parameter and data selection are common strategies for reducing fine-tuning cost, yet they are typically driven by separate scoring mechanisms. When a parameter mask and data subset jointly determine restricted fine-tuning, this separation incurs redundant overhead and makes coordinated selection difficult. We cast parameter and data selection as two bilevel selection problems under a common validation objective and derive a shared local response-surrogate scoring rule. Under first- and second-order validation-improvement approximations, parameter importance and data utility emerge as column-wise and row-wise aggregations of a single gradient interaction matrix, yielding a closed-form row-column correspondence for co-extracting both signals. Building on this structure, we propose DualSFT (Dual-Selection Fine-Tuning), a one-shot dual-scoring algorithm that produces a parameter mask and data subset from shared gradient statistics. On 3B-9B LLMs, single-axis DualSFT variants strengthen target-task performance and stability-plasticity trade-offs within their comparison groups, while full DualSFT yields a more favorable joint-constrained trade-off than sequential hybrid baselines under matched budgets.

Materials science data collection can be expensive, making the reuse and long-term utility of datasets critical important for future discovery campaigns. In practice, researchers prioritize a subset of properties due to research interests. However, ignoring a subset of outcomes in data collection campaigns potentially generate datasets poorly suited for future learning tasks. Here, we present a framework for dataset construction that maximizes informativeness for target properties of interest while preserving performance on untargeted ones. Our approach uses diversity-aware selection to ensure broad coverage of the materials space. In noisy experimental dataset construction, we find that without our diversity-aware framework, prediction performance on untargeted properties can degrade by up to 40% relative to random sampling, whereas applying our framework yields improvements of up to 10% . For targeted properties, performance can degrade with respect to random sampling by up to 12.5% without diversity, while our framework achieves gains of up to 25%. Incorporating diversity into dataset construction not only preserves informativeness for the targeted properties, but also improves materials coverage for potential future objectives. As a result, the constructed datasets remain broadly informative across considered and unconsidered outcomes, ensuring unbiased quality entries and mitigating cold-start limitations in subsequent modeling and discovery campaigns.

While mechanistic interpretability tools like Sparse Autoencoders (SAEs) can uncover meaningful features within Large Language Models (LLMs), a critical gap remains in transforming these insights into practical actions for model optimization. We bridge this gap with the hypothesis that data selection guided by a model's internal task features is a effective training strategy. Inspired by this, we propose Interpretability-Guided Data Selection (IGDS), a framework that first identifies these causal task features through frequency recall and interventional filtering, then selects ``Feature-Resonant Data'' that maximally activates task features for fine-tuning. We validate IGDS on mathematical reasoning, summarization, and translation tasks within Gemma-2, LLaMA-3.1, and Qwen3 models. Our experiments demonstrate exceptional data efficiency: on the Math task, IGDS surpasses full-dataset fine-tuning by a remarkable 17.4% on Gemma-2-2B while using only 50% of the data, and outperforms established baselines focused on data quality and diversity. Analysis confirms a strong positive correlation between feature amplification and task performance improvement. IGDS thus provides a direct and effective framework to enhance LLMs by leveraging their internal mechanisms, validating our core hypothesis.

Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an instruction data selection framework based on weighted in-context influence (wICI), which measures how effectively each candidate example reduces instruction-following difficulty for semantically related peers. Through systematic experiments, we address three key questions: what constitutes effective instruction tuning data from an in-context perspective, whether sample difficulty correlates with in-context influence, and how in-context influence translates to instruction tuning effectiveness. Experiments across multiple models and benchmarks demonstrate that our method consistently outperforms existing baselines under constrained data budgets, while empirically showing that sample difficulty negatively correlates with in-context influence.

When, in terms of the number of data points, the size of a dataset exceeds available computing resources, or when labeling is expensive, an attractive solution consists of selecting only some of the data points (subdata) for further consideration. A central question for selecting subdata of size $n$ from $N$ available data points is which $n$ points to select. While an answer to this question depends on the objective, one approach for a parametric model and a focus on parameter estimation is to select subdata that retains maximal information. Identifying such subdata is a classical NP-hard problem due to its inherent discreteness. Based on optimal approximate design theory, we develop a new methodology for information-based subdata selection, resulting in subdata that approaches the optimal solution. To achieve this, we develop a novel algorithm that applies to a general model, accommodates arbitrary choices of $N$ and $n$, and supports multiple optimality criteria, and we prove its convergence. Moreover, the new methodology facilitates an assessment of the efficiency of subdata selected by any method by obtaining tight lower and upper bounds for the efficiency. We show that the subdata obtained through the new methodology is highly efficient and outperforms all existing methods.

Mutants support testing and debugging in two roles: (i) as test goals and (ii) as substitutes for real faults. Hard-to-kill mutants provide better guidance for test improvement, while realism is essential when mutants are used to simulate real bugs. Building on these roles, selective mutation for deep learning (DL) aims to reduce the cost of mutant generation and execution by choosing operator configurations that yield resistant and realistic mutants. However, the DL literature lacks a unified measure that captures both aspects. This study presents a probabilistic framework to quantify mutant quality along two complementary axes: resistance and realism. Resistance adapts the classical notion of hard-to-kill mutants to the DL setting using statistical killing probabilities, while realism is measured via the generalized Jaccard similarity between mutant and real-fault detectability patterns. The framework enables ranking and filtering of low-quality mutation-operator configurations without assuming a specific use case. We empirically evaluate the approach on four datasets of real DL faults. Three datasets (CleanML, DeepFD, and DeepLocalize) are used to estimate and select high-quality operator configurations, and the held-out defect4ML dataset is used for validation. Results show that quality-driven selection reduces the number of generated mutants by up to 55.6% while preserving typical levels of resistance and realism under baseline-aligned selection thresholds. These findings confirm that dual-objective selection can lower cost without compromising the usefulness of mutants for either role.

Automating the detection of regulatory compliance remains a challenging task due to the complexity and variability of legal texts. Models trained on one regulation often fail to generalise to others. This limitation underscores the need for principled methods to improve cross-domain transfer. We study data selection as a strategy to mitigate negative transfer in compliance detection framed as a natural language inference (NLI) task. Specifically, we evaluate four approaches for selecting augmentation data from a larger source domain: random sampling, Moore-Lewis's cross-entropy difference, importance weighting, and embedding-based retrieval. We systematically vary the proportion of selected data to analyse its effect on cross-domain adaptation. Our findings demonstrate that targeted data selection substantially reduces negative transfer, offering a practical path toward scalable and reliable compliance automation across heterogeneous regulations.