Papers with few-shot learning methods
ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios (2026.tacl-1)
Copied to clipboard
| Challenge: | Active learning strategies struggle with a ‘cold-start’ problem, needing substantial initial data to be effective. |
| Approach: | They propose an active learning approach that leverages Large Language Models such as GPT-4, o1, Llama 3, or Mistral Large for selecting instances. |
| Outcome: | The proposed approach outperforms existing methods ADAPET, PERFECT, and SetFit in few-shot scenarios and can be extended to non-few scenarios. |
LEA: Meta Knowledge-Driven Self-Attentive Document Embedding for Few-Shot Text Classification (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing few-shot text classification methods often lack labeled data in real-world tasks. |
| Approach: | They propose a meta-learning method that encodes how to attend for given tasks . they evaluate the method on five benchmark datasets and show it is competitive . |
| Outcome: | The proposed method performs better on five benchmark datasets than previous methods on labeled data. |
IsOBS: An Information System for Oracle Bone Script (2020.emnlp-demos)
Copied to clipboard
| Challenge: | Oracle bone script (OBS) documents are the oldest continuously-used writing system in the world and are important for linguistic and historical research. |
| Approach: | They construct an information system for OBS to symbolize, serialize, and store OBS data at the character-level using efficient databases and retrieval modules. |
| Outcome: | The proposed system symbolizes, serializes, and stores OBS data at the character-level, based on efficient databases and retrieval modules. |
Using dependency parsing for few-shot learning in distributional semantics (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for few-shot learning use dependency parsing information to learn meaning of rare words based on limited amount of context sentences. |
| Approach: | They propose dependency parsing for few-shot learning to learn meaning of rare words . they use word embedding models as background spaces for few shot learning . |
| Outcome: | The proposed methods enhance the additive baseline model by using dependencies. |
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models that pursue rapid generalization to new tasks are mostly trained in a single shot on fixed datasets, unable to dynamically expand their knowledge. |
| Approach: | They propose a new learning setup that assumes a model learns from a sequence of diverse NLP tasks arriving sequentially, accumulating knowledge for improved generalization to new tasks. |
| Outcome: | The proposed learning setup improves generalization ability while retaining performance on the tasks learned earlier. |
Automated Few-Shot Classification with Instruction-Finetuned Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing few-shot learning approaches combine language models with prompts, but they often require domain knowledge and substantial guesswork. |
| Approach: | They propose a method to eliminate the need for handcrafted prompts by generating two distinct, semantically meaningful class descriptions and a selection mechanism via cross-validation. |
| Outcome: | The proposed method outperforms state-of-the-art few-shot learning methods over 12 datasets, spanning 8 classification tasks. |
MetaSLRCL: A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing few-shot text classification methods lack labeled data in many scenarios. |
| Approach: | They propose a meta learning framework that obtains different learning rates for different tasks and neural network layers to enable the meta learner to quickly adapt to new training data. |
| Outcome: | The proposed framework can obtain different learning rates for different tasks and neural network layers so as to enable the meta learner to quickly adapt to new tasks. |
Cross-domain Named Entity Recognition via Graph Matching (2022.findings-acl)
Copied to clipboard
| Challenge: | Empirical results show that our method outperforms a series of transfer learning, multitask learning, and few-shot learning methods due to the data scarcity in the real-world scenario. |
| Approach: | They propose to model the label relationship as a probability distribution and construct label graphs in both source and target label spaces. |
| Outcome: | Empirical results show that the proposed method outperforms transfer learning, multi-task learning, and few-shot learning methods on four datasets. |
Prompt-free and Efficient Few-shot Learning with Language Models (2022.acl-long)
Copied to clipboard
Rabeeh Karimi Mahabadi, Luke Zettlemoyer, James Henderson, Lambert Mathias, Marzieh Saeidi, Veselin Stoyanov, Majid Yazdani
| Challenge: | Existing methods for few-shot fine-tuning of pretrained language models require carefully engineered prompts and verbalizers to convert inputs into a cloze-format that the PLM can score. |
| Approach: | They propose a method for few-shot fine-tuning of pretrained language models that uses task-specific adapters instead of manually engineered prompts and verbalizers. |
| Outcome: | The proposed method outperforms existing state-of-the-art methods on a wide range of few shot NLP tasks. |
On Measuring the Intrinsic Few-Shot Hardness of Datasets (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has shown that few-shot learning is successful for pre-trained models, but there is no concrete understanding of when and why it is successful. |
| Approach: | They propose a simple metric that estimates few-shot hardness for a given dataset . they propose metric which exploits feature-space invariances between training and test samples . |
| Outcome: | The proposed metric better accounts for few-shot hardness compared to existing notions and is 8-100x faster to compute. |
Noisy Channel Language Model Prompting for Few-Shot Text Classification (2022.acl-long)
Copied to clipboard
| Challenge: | Prior work has suggested methods for finding better prompt or scoring of the output from the model. |
| Approach: | They propose a noisy channel approach for language model prompting in few-shot text classification by in-context demonstration or prompt tuning. |
| Outcome: | The proposed model outperforms direct models in both demonstration and prompt tuning. |
FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (D18-1)
Copied to clipboard
| Challenge: | Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans. |
| Approach: | They propose a Few-Shot Relation Classification Dataset consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers. |
| Outcome: | The proposed methods perform well on the most competitive few-shot learning models, especially as compared with humans. |
Quantile Regression with Large Language Models for Price Prediction (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to structured prediction tasks focus on point estimates and lack systematic comparison across different methods. |
| Approach: | They propose a novel quantile regression approach that enables LLMs to produce full predictive distributions, improving upon traditional point estimates. |
| Outcome: | The proposed model outperforms encoder architectures, embedding-based methods, and few-shot learning methods in prediction accuracy and distributional calibration. |
AMAL: Meta Knowledge-Driven Few-Shot Adapter Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained language models fail to yield meaningful results in the few-shot regime. |
| Approach: | They propose a meta-learning-driven low-rank adapter pooling method for leveraging pre-trained language models even with just a few data points. |
| Outcome: | The proposed method outperforms previous few-shot learning methods on five text classification benchmark datasets. |