GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling

• URL: http://arxiv.org/abs/2606.04516v1
• Date: Wed, 03 Jun 2026 06:47:50 GMT
• Title: GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling
• Abstract summary: Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning.<n>It faces a dilemma: standard supervised scaling is throttled by high annotation costs, while unsupervised alternatives suffer from severe model collapse.<n>Recent semi-supervised RLVR methods address this by using a small labeled set to guide unlabeled data, achieving a promising trade-off between training efficacy and annotation cost.<n>We propose GeoMin, which models global feature on distributions labeled data to decode the structural discrepancy between correct and incorrect rollouts.
• Score: 29.20321049470364
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is throttled by high annotation costs, while unsupervised alternatives suffer from severe model collapse. Recent semi-supervised RLVR methods address this by using a small labeled set to guide unlabeled data, achieving a promising trade-off between training efficacy and annotation cost. However, they suffer from a severe data-efficiency bottleneck due to the reliance on coarse performance heuristics, leaving a vast majority of valuable instances underutilized. To this end, we propose GeoMin, which models global feature distributions on labeled data to decode the structural discrepancy between correct and incorrect rollouts, thereby establishing a robust prior to assess the reliability of self-reward signals and fully unleash the potential of unlabeled data. Empirically, GeoMin outperforms the strongest baselines by +4.1% and even surpasses fully supervised models with only 10% of the annotations, demonstrating remarkable data efficiency.

Related papers

• Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots [29.141492387722963]
  "Pick in the dark" setup for RLVR aims to select, without prior supervision, unlabeled samples that are most beneficial for training and worthy of annotation.<n>We propose PivotTrace, a three-way data triage framework that leverages attention dynamics to trace metacognitive pivots during reasoning.
  arXiv  Detail & Related papers  (2026-06-03T06:34:42Z)
• Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis [68.28714988482703]
  Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs)<n>We present a study revealing that general-domain PRMs struggle to supervise data analysis agents.<n>We introduce DataPRM, a novel environment-aware generative process reward model.
  arXiv  Detail & Related papers  (2026-04-27T09:00:30Z)
• Fault-Tolerant Evaluation for Sample-Efficient Model Performance Estimators [13.227055178509524]
  We propose a fault-tolerant evaluation framework that integrates bias and variance considerations within an adjustable tolerance level.<n>We show that proper calibration of $varepsilon$ ensures reliable evaluation across different variance regimes.<n> Experiments on real-world datasets demonstrate that our framework provides comprehensive and actionable insights into estimator behavior.
  arXiv  Detail & Related papers  (2026-02-06T22:14:46Z)
• Labels Matter More Than Models: Quantifying the Benefit of Supervised Time Series Anomaly Detection [56.302586730134806]
  Time series anomaly detection (TSAD) is a critical data mining task often constrained by label scarcity.<n>Current research predominantly focuses on Unsupervised Time-series Anomaly Detection.<n>This paper challenges the premise that architectural complexity is the optimal path for TSAD.
  arXiv  Detail & Related papers  (2025-11-20T08:32:49Z)
• Heterogeneous Self-Supervised Acoustic Pre-Training with Local Constraints [64.15709757611369]
  We propose a new self-supervised pre-training approach to dealing with heterogeneous data.<n>The proposed approach can significantly improve the adaptivity of the self-supervised pre-trained model for the downstream supervised fine-tuning tasks.
  arXiv  Detail & Related papers  (2025-08-27T15:48:50Z)
• Distributionally Robust Optimization with Adversarial Data Contamination [49.89480853499918]
  We focus on optimizing Wasserstein-1 DRO objectives for generalized linear models with convex Lipschitz loss functions.<n>Our primary contribution lies in a novel modeling framework that integrates robustness against training data contamination with robustness against distributional shifts.<n>This work establishes the first rigorous guarantees, supported by efficient computation, for learning under the dual challenges of data contamination and distributional shifts.
  arXiv  Detail & Related papers  (2025-07-14T18:34:10Z)
• Semi-supervised Node Importance Estimation with Informative Distribution Modeling for Uncertainty Regularization [13.745026710984469]
  We propose the first semi-supervised node importance estimation framework, i.e., EASING, to improve learning quality for unlabeled data in heterogeneous graphs.<n>Different from previous approaches, EASING explicitly captures uncertainty to reflect the confidence of model predictions.<n>Based on labeled and pseudo-labeled data, EASING develops effective semi-supervised heteroscedastic learning with varying node uncertainty regularization.
  arXiv  Detail & Related papers  (2025-03-26T16:27:06Z)
• Semi-Supervised Reward Modeling via Iterative Self-Training [52.48668920483908]
  We propose Semi-Supervised Reward Modeling (SSRM), an approach that enhances RM training using unlabeled data. We demonstrate that SSRM significantly improves reward models without incurring additional labeling costs. Overall, SSRM substantially reduces the dependency on large volumes of human-annotated data, thereby decreasing the overall cost and time involved in training effective reward models.
  arXiv  Detail & Related papers  (2024-09-10T22:57:58Z)
• An Embedding is Worth a Thousand Noisy Labels [0.11999555634662634]
  We propose WANN, a weighted Adaptive Nearest Neighbor approach to address label noise.<n>We show WANN outperforms reference methods on diverse datasets of varying size and under various noise types and severities.<n>Our approach, emphasizing efficiency and explainability, emerges as a simple, robust solution to overcome inherent limitations of deep neural network training.
  arXiv  Detail & Related papers  (2024-08-26T15:32:31Z)
• Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances [55.37242480995541]
  We propose to denoise noisy NER data with guidance from a small set of clean instances. Along with the main NER model we train a discriminator model and use its outputs to recalibrate the sample weights. Results on public crowdsourcing and distant supervision datasets show that the proposed method can consistently improve performance with a small guidance set.
  arXiv  Detail & Related papers  (2023-10-25T17:23:37Z)
• Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods [24.190587751595455]
  Weak supervision is a popular method for building machine learning models without relying on ground truth annotations. Existing approaches use latent variable estimation to model the noisy sources. We show that for a class of latent variable models highly applicable to weak supervision, we can find a closed-form solution to model parameters. We use this insight to build FlyingSquid, a weak supervision framework that runs orders of magnitude faster than previous weak supervision approaches.
  arXiv  Detail & Related papers  (2020-02-27T07:51:50Z)

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.