UCS: Estimating Unseen Coverage for Improved In-Context Learning

• URL: http://arxiv.org/abs/2604.12015v1
• Date: Mon, 13 Apr 2026 20:00:41 GMT
• Title: UCS: Estimating Unseen Coverage for Improved In-Context Learning
• Abstract summary: Unseen Coverage Selection (UKS) is a training-free, subset-level coverage prior motivated by the principle that a good demonstration set should expose the model to latent cluster unrevealed by the currently selected subset.<n>UCS operationalizes this idea by inducing discrete latent clusters from model-consistent embeddings and estimating the number of unrevealed clusters within a candidate subset via a Smoothed Good-contexting estimator from its empirical frequency spectrum.<n> Experiments on multiple intent-classification and reasoning benchmarks with frontier Large Language Models show that augmenting strong baselines with UCS consistently improves ICL accuracy by up to 2-6% under the same
• Score: 24.34094317236037
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In-context learning (ICL) performance depends critically on which demonstrations are placed in the prompt, yet most existing selectors prioritize heuristic notions of relevance or diversity and provide limited insight into the coverage of a demonstration set. We propose Unseen Coverage Selection (UKS), a training-free, subset-level coverage prior motivated by the principle that a good demonstration set should expose the model to latent cluster unrevealed by the currently selected subset. UCS operationalizes this idea by (1) inducing discrete latent clusters from model-consistent embeddings and (2) estimating the number of unrevealed clusters within a candidate subset via a Smoothed Good--Turing estimator from its empirical frequency spectrum. Unlike previous selection methods, UCS is coverage-based and training-free, and can be seamlessly combined with both query-dependent and query-independent selection baselines via a simple regularized objective. Experiments on multiple intent-classification and reasoning benchmarks with frontier Large Language Models show that augmenting strong baselines with UCS consistently improves ICL accuracy by up to 2-6% under the same selection budget, while also yielding insights into task- and model-level latent cluster distributions. Code is available at https://github.com/Raina-Xin/UCS.

Related papers

• Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agents [81.79110139097297]
  General-purpose embedding models excel at recognizing semantic similarities but fail to capture the characteristics of texts specified by user instructions.<n>We reframe instruction-following clustering as a generative task and train large reasoning models as autonomous clustering agents.<n>Our reasoning-driven training pipeline enables LRMs to interpret high-level clustering instructions and then infer the corresponding latent groupings.
  arXiv  Detail & Related papers  (2026-03-06T10:15:54Z)
• DiEC: Diffusion Embedded Clustering [0.76629754443761]
  Deep clustering critically depends on representations that expose clear cluster structure.<n>Most prior methods learn a single embedding with an autoencoder or a self-supervised encoder and treat it as the primary representation for clustering.<n>We propose Embedded Diffusion Clustering (DiEC), an unsupervised clustering framework that exploits this trajectory by directly leveraging intermediate activations of a pretrained diffusion U-Net.
  arXiv  Detail & Related papers  (2025-12-24T03:10:00Z)
• S$^2$FS: Spatially-Aware Separability-Driven Feature Selection in Fuzzy Decision Systems [45.05989432332541]
  We propose spatially-aware Separability-driven Feature Selection (S$2$FS) for fuzzy decision systems.<n>S$2$FS is guided by a spatially-aware separability criterion that considers within-class compactness and between-class separation.<n>Experiments on ten real-world datasets demonstrate that S$2$FS consistently outperforms eight state-of-the-art feature selection algorithms.
  arXiv  Detail & Related papers  (2025-09-30T06:30:14Z)
• Towards Compute-Optimal Many-Shot In-Context Learning [69.38428467281862]
  We propose two strategies for demonstration selection in many-shot ICL.<n>First method combines a small number of demonstrations, selected based on similarity to each test sample, with a disproportionately larger set of random demonstrations that are cached.<n>Second strategy improves the first by replacing random demonstrations with those selected using centroids derived from test sample representations via k-means clustering.
  arXiv  Detail & Related papers  (2025-07-22T04:21:03Z)
• CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning [80.18781219542016]
  Continual Learning (CL) empowers AI models to continuously learn from sequential task streams.<n>Recent parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance.<n>We propose Cross-subspace Knowledge Alignment and Aggregation (CKAA) to enhance robustness against misleading task-ids.
  arXiv  Detail & Related papers  (2025-07-13T03:11:35Z)
• Split Matching for Inductive Zero-shot Semantic Segmentation [56.47556212515178]
  Zero-shot Semantic (ZSS) aims to segment categories that are not annotated during training.<n>We propose Split Matching (SM), a novel assignment strategy that decouples Hungarian matching into two components.<n>SM is the first to introduce decoupled Hungarian matching under the inductive ZSS setting, and achieves state-of-the-art performance on two standard benchmarks.
  arXiv  Detail & Related papers  (2025-05-08T07:56:30Z)
• Demonstration Selection for In-Context Learning via Reinforcement Learning [16.103533806505403]
  Relevance-Diversity Enhanced Selection (RDES) is an innovative approach to optimize the selection of diverse reference demonstrations.<n>RDES employs frameworks like Q-learning and a PPO-based variant to dynamically identify demonstrations that maximize diversity.<n>We demonstrate that RDES significantly enhances performance compared to ten established baselines.
  arXiv  Detail & Related papers  (2024-12-05T08:33:52Z)
• A One-shot Framework for Distributed Clustered Learning in Heterogeneous Environments [54.172993875654015]
  The paper proposes a family of communication efficient methods for distributed learning in heterogeneous environments. One-shot approach, based on local computations at the users and a clustering based aggregation step at the server is shown to provide strong learning guarantees. For strongly convex problems it is shown that, as long as the number of data points per user is above a threshold, the proposed approach achieves order-optimal mean-squared error rates in terms of the sample size.
  arXiv  Detail & Related papers  (2022-09-22T09:04:10Z)
• Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods [61.49061000562676]
  We introduce Cluster Learnability (CL) to assess learnability. CL is measured in terms of the performance of a KNN trained to predict labels obtained by clustering the representations with K-means. We find that CL better correlates with in-distribution model performance than other competing recent evaluation schemes.
  arXiv  Detail & Related papers  (2022-06-02T19:05:13Z)
• Pool-based sequential active learning with multi kernels [10.203602318836444]
  We study a pool-based sequential active learning (AL) in which one sample is queried at each time from a large pool of unlabeled data. We propose two selection criteria, named expected- Kerneldiscrepancy (EKD) and expected- Kernel-loss (EKL) Also, it is identified that the proposed EKD and EKL successfully generalize the concepts of popular query-by-committee (QBC) and expected-model-change (EMC)
  arXiv  Detail & Related papers  (2020-10-22T03:54:41Z)
• Covariance-engaged Classification of Sets via Linear Programming [16.11804985840274]
  Set classification aims to classify a set of observations as a whole, as opposed to classifying individual observations separately. We show that the number of observations in the set plays a critical role in bounding the Bayes risk. Under this framework, we propose new methods of set classification.
  arXiv  Detail & Related papers  (2020-06-26T07:20:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.