mlsanityData to 14 Oct 2026

DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning

arXiv 2502.00305 ↗First posted 1 Feb 2025cs.CL cs.AI cs.IRcited by 2

Not on the map. Why?

Abstract (arXiv)

Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarce text classification. However, existing CSAL methods overlook weak classes and hard representative examples, resulting in biased learning. To address these issues, this paper proposes a novel dual-diversity enhancing and uncertainty-aware (DEUCE) framework for CSAL. Specifically, DEUCE leverages a pretrained language model (PLM) to efficiently extract textual representations, class predictions, and predictive uncertainty. Then, it constructs a Dual-Neighbor Graph (DNG) to combine information on both textual diversity and class diversity, ensuring a balanced data distribution. It further propagates uncertainty information via density-based clustering to select hard representative instances. DEUCE performs well in selecting class-balanced and hard representative data by dual-diversity and informativeness. Experiments on six NLP datasets demonstrate the superiority and efficiency of DEUCE.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 44 of its 77 references that are in the map. First posted on arXiv 1 Feb 2025.

Builds on

44 of 77 references.

References · 44

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  7. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  8. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  9. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  10. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  11. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  12. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
32 more
  1. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  2. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 395
  3. 2022TabLLM: Few-shot Classification of Tabular Data with Large Language Modelscited by 277
  4. 2019Representation Degeneration Problem in Training Natural Language Generation Modelscited by 255
  5. 2021A Survey of Human-in-the-loop for Machine Learningcited by 215
  6. 2021Active Learning by Acquiring Contrastive Examplescited by 156
  7. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  8. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  9. 2023Scaling Sentence Embeddings with Large Language Modelscited by 85
  10. 2022PromptBERT: Improving BERT Sentence Embeddings with Promptscited by 75
  11. 2023Calibration in Deep Learning: A Survey of the State-of-the-Artcited by 75
  12. 2021Revisiting Uncertainty-based Query Strategies for Active Learning with Transformerscited by 60
  13. 2023Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Servicescited by 43
  14. 2018Weakly-Supervised Hierarchical Text Classificationcited by 42
  15. 2022A Survey of Active Learning for Natural Language Processingcited by 40
  16. 2020Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networkscited by 31
  17. 2022On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliencycited by 31
  18. 2021On Training Instance Selection for Few-Shot Neural Text Generationcited by 26
  19. 2021A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classificationcited by 17
  20. 2023Large Language Models are Fixated by Red Herrings: Exploring Creative Problem Solving and Einstellung Effect using the Only Connect Wall Datasetcited by 17
  21. 2022Cluster & Tune: Boost Cold Start Performance in Text Classificationcited by 13
  22. 2023Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Taskscited by 13
  23. 2022Active Few-Shot Learning with FASLcited by 11
  24. 2024Green AI: A Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructurescited by 11
  25. 2022All models are wrong, but which are useful? Comparing parametric and nonparametric estimation of causal effects in finite samplescited by 6
  26. 2021Mitigating Sampling Bias and Improving Robustness in Active Learningcited by 5
  27. 2023DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspectivecited by 5
  28. 2023Utilising a Large Language Model to Annotate Subject Metadata: A Case Study in an Australian National Research Data Cataloguecited by 4
  29. 2020Comprehensive and Efficient Data Labeling via Adaptive Model Schedulingcited by 3
  30. 2021Addressing practical challenges in Active Learning via a hybrid query strategycited by 2
  31. 2022Cold Start Active Learning Strategies in the Context of Imbalanced Classificationcited by 2
  32. 2022SLOVA: Uncertainty Estimation Using Single Label One-Vs-All Classifiercited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2026LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendationcited by 1
  2. 2025Cold-Start Active Preference Learning in Socio-Economic Domainscited by 0