# Efficient, Uncertainty-based Moderation of Neural Networks Text Classifiers

arXiv: https://arxiv.org/abs/2204.01334 · HTML: https://mlsanity.com/paper/2204.01334/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis](https://mlsanity.com/paper/1701.08118/) (2017)
- [Quantifying Uncertainties in Natural Language Processing Tasks](https://mlsanity.com/paper/1811.07253/) (2018)
- [Classification Under Human Assistance](https://mlsanity.com/paper/2006.11845/) (2020)
- [Deep Learning for User Comment Moderation](https://mlsanity.com/paper/1705.09993/) (2017)
- [Self-Checking Deep Neural Networks in Deployment](https://mlsanity.com/paper/2103.02371/) (2021)
- [Classifying Multilingual User Feedback using Traditional Machine Learning and Deep Learning](https://mlsanity.com/paper/1909.05504/) (2019)
- [To BAN or not to BAN: Bayesian Attention Networks for Reliable Hate Speech Detection](https://mlsanity.com/paper/2007.05304/) (2020)
- [Improving Moderation of Online Discussions via Interpretable Neural Models](https://mlsanity.com/paper/1809.06906/) (2018)

## Built on by (most cited first, 7 of 7)

- [Uncertainty in Natural Language Processing: Sources, Quantification, and Applications](https://mlsanity.com/paper/2306.04459/) (2023)
- [Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2405.03425/) (2024)
- [Tailoring Requirements Engineering for Responsible AI](https://mlsanity.com/paper/2302.10816/) (2023)
- [Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization](https://mlsanity.com/paper/2409.11212/) (2024)
- [Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling](https://mlsanity.com/paper/2302.08659/) (2023)
- [A multi-model-based deep learning framework for short text multiclass classification with the imbalanced and extremely small data set](https://mlsanity.com/paper/2206.12027/) (2022)
- [Exploring Human-in-the-Loop Themes in AI Application Development: An Empirical Thematic Analysis](https://mlsanity.com/paper/2603.05510/) (2026)

## Abstract (arXiv)

To maximize the accuracy and increase the overall acceptance of text classifiers, we propose a framework for the efficient, in-operation moderation of classifiers' output. Our framework focuses on use cases in which F1-scores of modern Neural Networks classifiers (ca.~90%) are still inapplicable in practice. We suggest a semi-automated approach that uses prediction uncertainties to pass unconfident, probably incorrect classifications to human moderators. To minimize the workload, we limit the human moderated data to the point where the accuracy gains saturate and further human effort does not lead to substantial improvements. A series of benchmarking experiments based on three different datasets and three state-of-the-art classifiers show that our framework can improve the classification F1-scores by 5.1 to 11.2% (up to approx.~98 to 99%), while reducing the moderation load up to 73.3% compared to a random moderation.