mlsanityData to 14 Oct 2026

Automated Few-shot Classification with Instruction-Finetuned Language Models

arXiv 2305.12576 ↗First posted 21 May 2023cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

A particularly successful class of approaches for few-shot learning combines language models with prompts -- hand-crafted task descriptions that complement data samples. However, designing prompts by hand for each task commonly requires domain knowledge and substantial guesswork. We observe, in the context of classification tasks, that instruction finetuned language models exhibit remarkable prompt robustness, and we subsequently propose a simple method to eliminate the need for handcrafted prompts, named AuT-Few. This approach consists of (i) a prompt retrieval module that selects suitable task instructions from the instruction-tuning knowledge base, and (ii) the generation of two distinct, semantically meaningful, class descriptions and a selection mechanism via cross-validation. Over 12 datasets, spanning 8 classification tasks, we show that AuT-Few outperforms current state-of-the-art few-shot learning methods. Moreover, AuT-Few is the best ranking method across datasets on the RAFT few-shot benchmark. Notably, these results are achieved without task-specific handcrafted prompts on unseen tasks.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 39 of its 64 references that are in the map. First posted on arXiv 21 May 2023.

Builds on

39 of 64 references.

References · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2020Scaling Laws for Neural Language Modelscited by 6,586
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  5. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  6. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  7. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  8. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  9. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  10. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 807
  11. 2021GPT Understands, Toocited by 716
  12. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 669
27 more
  1. 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 460
  2. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  3. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 377
  4. 2018WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representationscited by 372
  5. 2021Do Prompt-Based Models Really Understand the Meaning of their Prompts?cited by 326
  6. 2018SentEval: An Evaluation Toolkit for Universal Sentence Representationscited by 294
  7. 2022PromptSource: An Integrated Development Environment and Repository for Natural Language Promptscited by 289
  8. 2021SPoT: Better Frozen Model Adaptation through Soft Prompt Transfercited by 235
  9. 2021WARP: Word-level Adversarial ReProgrammingcited by 221
  10. 2021When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Datasetcited by 201
  11. 2021Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classificationcited by 183
  12. 2022Efficient Few-Shot Learning Without Promptscited by 137
  13. 2022ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Promptscited by 85
  14. 2018CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Servicecited by 73
  15. 2021Template-free Prompt Tuning for Few-shot NERcited by 73
  16. 2023Parameter-Efficient Fine-Tuning Design Spacescited by 67
  17. 2021Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameterscited by 66
  18. 2022Prototypical Verbalizer for Prompt-based Few-shot Tuningcited by 53
  19. 2021I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviewscited by 45
  20. 2021RAFT: A Real-World Few-Shot Text Classification Benchmarkcited by 44
  21. 2022Unsupervised Cross-Task Generalization via Retrieval Augmentationcited by 42
  22. 2022PERFECT: Prompt-free and Efficient Few-shot Learning with Language Modelscited by 40
  23. 2021True Few-Shot Learning with Prompts -- A Real-World Perspectivecited by 38
  24. 2019Automatically Identifying Complaints in Social Mediacited by 25
  25. 2021AI Ethics Statements -- Analysis and lessons learnt from NeurIPS Broader Impact Statementscited by 16
  26. 2022Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classificationcited by 8
  27. 2022SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 0; 2026: 1.

9 papers.

  1. 2023QA-NatVer: Question Answering for Natural Logic-based Fact Verificationcited by 8
  2. 2024Toxicity Classification in Ukrainiancited by 7
  3. 2024Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuningcited by 7
  4. 2024Cross-lingual Text Classification Transfer: The Case of Ukrainiancited by 5
  5. 2024Questionable practices in machine learningcited by 4
  6. 2024Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classescited by 3
  7. 2024Evaluation of Few-Shot Learning for Classification Tasks in the Polish Languagecited by 1
  8. 2024Generating Synthetic Datasets for Few-shot Prompt Tuningcited by 1
  9. 2026The Overlooked Repetitive Lengthening Form in Sentiment Analysiscited by 1