Papers with self-training methods

8 papers
Friend-training: Learning from Models of Different but Related Tasks (2023.eacl-main)

Copied to clipboard

Challenge: Current self-training methods focus on improving model performance on a single task.
Approach: They propose a cross-task self-training framework where models trained to do different tasks are used in iterative training, pseudo-labeling, and retraining processes to help each other for better selection of pseudo-labeled labels.
Outcome: The proposed framework achieves the best performance compared to baselines on two dialogue understanding tasks.
Semi-supervised Relation Extraction via Incremental Meta Self-Training (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods suffer from the gradual drift problem, where noisy pseudo labels are incorporated during training.
Approach: They propose a method that uses pseudo labels to assess quality on unlabeled samples . they use a relation label generation network to learn from successful and failed attempts .
Outcome: Experimental results show the proposed method can improve on two public datasets.
Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for self-training from meaning representations (MRs) are noisy or uninformative for the model to learn from.
Approach: They propose a two-phase procedure to generate high-quality pseudo-labeled MR-to-Text pairs by aggregating multiple perturbed latent representations from each MR.
Outcome: Empirical results on two benchmark datasets show that the proposed procedure outperforms existing methods on automatic and human evaluations.
Zero-shot Text Classification via Reinforced Self-training (2020.acl-main)

Copied to clipboard

Challenge: Existing methods to learn from unlabeled data are difficult for zero-shot text classification tasks.
Approach: They propose a self-training based method to efficiently leverage unlabeled data.
Outcome: The proposed method significantly outperforms existing methods in zero-shot text classification tasks on benchmarks and a real-world e-commerce dataset.
EICO: Improving Few-Shot Text Classification via Explicit and Implicit Consistency Regularization (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods for few-shot text classification are limited by labeled data.
Approach: They propose to use consistency regularization to improve few-shot text classification by generating pseudo-labels from weakly-augmented and strongly-augmented views.
Outcome: The proposed method achieves competitive performance with 16 labeled examples with prompt and verbalizer.
LLM-enhanced Self-training for Cross-domain Constituency Parsing (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to self-training rely on limited and potentially low-quality raw corpora.
Approach: They propose to enhance self-training with the large language model to generate domain-specific raw corpora iteratively and introduce grammar rules that guide the LLM in generating raw corporeals and establish criteria for selecting pseudo instances.
Outcome: The proposed method outperforms traditional methods regardless of the large language model's performance.
Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to fine-tune Large Language Models without human annotations are lacking in the field of natural language training.
Approach: They propose an environment-guided neural-symbolic self-training framework to overcome two main challenges: the scarcity of symbolic data and the limited proficiency of LLMs in processing symbolic language.
Outcome: The proposed framework overcomes two main challenges: the scarcity of symbolic data, and the limited proficiency of LLMs in processing symbolic language.
Self-Training Large Language Models with Confident Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models generate reasoning paths before final answers, but learning such a path requires costly human supervision.
Approach: They propose a method that fine-tunes LLMs to prefer reasoning paths with high confidence . they propose 'cORE-PO' that fine tunes Lms to choose high-quality reasoning paths .
Outcome: The proposed method improves the accuracy of outputs on four in-distribution and two out-of-difference benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations