Challenge: Abstractive text summarization (ATS) requires laborious data annotation and time-consuming model training.
Approach: They propose a novel active learning framework that asks large language models to rate difficulty of instances and then uses certainty gain maximization to select instances with a distribution that aligns well with the overall distribution.
Outcome: The proposed framework improves stability, effectiveness, and efficiency of abstractive text summarization backbones.

Similar Papers

Active Learning for Abstractive Text Summarization (2022.findings-emnlp)

Copied to clipboard

Challenge: Abstractive text summarization (ATS) requires a long document and short summaries.
Approach: They propose a query strategy for AL in abstractive text summarization that uses uncertainty estimation to reduce model performance.
Outcome: The proposed query strategy improves ROUGE and consistency scores for annotated datasets . it also increases the performance of the model, compared to passive annotation.
From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been used for selection and training of data for active learning.
Approach: They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop.
Outcome: The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances.
Reassessing Active Learning Adoption in Contemporary NLP: A Community Survey (2026.eacl-long)

Copied to clipboard

Challenge: a longstanding strategy to reduce annotation costs is active learning . data annotation is expected to remain important and active learning to stay relevant .
Approach: They conduct an online survey to assess the perceived relevance of data annotation and active learning . they propose a strategy to reduce annotation costs using active learning, an iterative process .
Outcome: The proposed strategies reduce setup complexity and uncertainty cost while maintaining model performance.
GSum: A General Framework for Guided Neural Abstractive Summarization (2021.naacl-main)

Copied to clipboard

Challenge: Abstractive summarization models are flexible, but they can be difficult to control.
Approach: They propose a general and extensible guided summarization framework that takes different kinds of guidance as input and perform experiments across different varieties.
Outcome: The proposed framework can generate more faithful summaries and different types of guidance generate qualitatively different summary.
BRIO: Bringing Order to Abstractive Summarization (2022.acl-long)

Copied to clipboard

Challenge: Abstractive summarization models are often trained with maximum likelihood estimation (MLE) . mLE assumes a deterministic (one-point) target distribution, but can cause performance degradation .
Approach: They propose a new training paradigm which assumes a non-deterministic distribution so that different candidate summaries are assigned probability mass according to their quality.
Outcome: The proposed model can estimate probabilities of candidate summaries that are more correlated with their level of quality.
Abstractive Text Summarization Using the BRIO Training Paradigm (2023.findings-acl)

Copied to clipboard

Challenge: Existing abstractive summarization models rely heavily on reference summaries and lack control over their performance.
Approach: They propose a BRIO paradigm to reduce the dependence on reference summaries by fine-tuning pre-trained language models and training them with the paradigm.
Outcome: The proposed paradigm outperforms existing models on Vietnamese and CNNDM datasets while maintaining the main content of the original text.
Active Learning for Natural Language Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to NLG are limited by the lack of annotated data.
Approach: They propose to use active learning to reduce the cost of manual annotation to improve annotation efficiency by selecting the most informative examples to label.
Outcome: The proposed approach surpasses baseline of random example selection in some cases but not in others.
On the Fragility of Active Learners for Text Classification (2024.emnlp-main)

Copied to clipboard

Challenge: Active learning (AL) techniques optimally utilize a labeling budget by iteratively selecting instances that are most valuable for learning.
Approach: They propose to use active learning techniques to iteratively select instances that are most valuable for learning.
Outcome: The proposed framework is used to benchmark active learning techniques for text classification using pre-trained representations.
Learning with Rejection for Abstractive Text Summarization (2022.emnlp-main)

Copied to clipboard

Challenge: Existing abstractive summarization systems produce non-factual summaries due to noise in the training dataset.
Approach: They propose a training objective for abstractive summarization based on rejection learning that learns whether or not to reject potentially noisy tokens.
Outcome: The proposed method significantly improves the factuality of generated summaries in automatic and human evaluations when compared to baseline models.
A Survey of Active Learning for Natural Language Processing (2022.emnlp-main)

Copied to clipboard

Challenge: Existing literature surveys on active learning for NLP are too specific or too general, covering deep active learning.
Approach: They propose to use active learning to improve model learning and annotation cost for NLP problems.
Outcome: The proposed approach is based on a large dataset of data-driven machine learning models.

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