# TestNUC: Enhancing Test-Time Computing Approaches and Scaling through Neighboring Unlabeled Data Consistency

arXiv: https://arxiv.org/abs/2502.19163 · HTML: https://mlsanity.com/paper/2502.19163/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 30 of 30)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning](https://mlsanity.com/paper/2305.14160/) (2023)
- [MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark](https://mlsanity.com/paper/2008.09335/) (2020)
- [Compositional Exemplars for In-context Learning](https://mlsanity.com/paper/2302.05698/) (2023)
- [Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation](https://mlsanity.com/paper/2305.16938/) (2023)
- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [Revisiting Demonstration Selection Strategies in In-Context Learning](https://mlsanity.com/paper/2401.12087/) (2024)
- [Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection](https://mlsanity.com/paper/1910.11621/) (2019)
- [kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference](https://mlsanity.com/paper/2303.13824/) (2023)
- [Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations](https://mlsanity.com/paper/2305.15035/) (2023)
- [A Survey on LLM Inference-Time Self-Improvement](https://mlsanity.com/paper/2412.14352/) (2024)
- [On the Noise Robustness of In-Context Learning for Text Generation](https://mlsanity.com/paper/2405.17264/) (2024)
- [JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification](https://mlsanity.com/paper/2310.14583/) (2023)
- [DeCrisisMB: Debiased Semi-Supervised Learning for Crisis Tweet Classification via Memory Bank](https://mlsanity.com/paper/2310.14577/) (2023)
- [GLEAN: Active Generalized Category Discovery with Diverse LLM Feedback](https://mlsanity.com/paper/2502.18414/) (2025)
- [BANGS: Game-Theoretic Node Selection for Graph Self-Training](https://mlsanity.com/paper/2410.09348/) (2024)

## Built on by (most cited first, 4 of 4)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents](https://mlsanity.com/paper/2506.18959/) (2025)
- [Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations](https://mlsanity.com/paper/2503.03062/) (2025)
- [Diagnosing Failures in Large Language Models' Answers: Integrating Error Attribution into Evaluation Framework](https://mlsanity.com/paper/2507.08459/) (2025)

## Abstract (arXiv)

Test-time computing approaches, which leverage additional computational resources during inference, have been proven effective in enhancing large language model performance. This work introduces a novel, linearly scaling approach, TestNUC, that improves test-time predictions by leveraging the local consistency of neighboring unlabeled data-it classifies an input instance by considering not only the model's prediction on that instance but also on neighboring unlabeled instances. We evaluate TestNUC across eight diverse datasets, spanning intent classification, topic mining, domain discovery, and emotion detection, demonstrating its consistent superiority over baseline methods such as standard prompting and self-consistency. Furthermore, TestNUC can be seamlessly integrated with existing test-time computing approaches, substantially boosting their performance. Our analysis reveals that TestNUC scales effectively with increasing amounts of unlabeled data and performs robustly across different embedding models, making it practical for real-world applications. Our code is available at https://github.com/HenryPengZou/TestNUC.