# CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models

arXiv: https://arxiv.org/abs/2306.03598 · HTML: https://mlsanity.com/paper/2306.03598/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 41 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [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)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [Probing Pretrained Language Models for Lexical Semantics](https://mlsanity.com/paper/2010.05731/) (2020)
- [On Identifiability in Transformers](https://mlsanity.com/paper/1908.04211/) (2019)
- [Getting a CLUE: A Method for Explaining Uncertainty Estimates](https://mlsanity.com/paper/2006.06848/) (2020)
- [Quantifying Uncertainties in Natural Language Processing Tasks](https://mlsanity.com/paper/1811.07253/) (2018)
- [Topic Modeling with Wasserstein Autoencoders](https://mlsanity.com/paper/1907.12374/) (2019)
- [Neural Models for Documents with Metadata](https://mlsanity.com/paper/1705.09296/) (2017)
- [Interpretation of NLP models through input marginalization](https://mlsanity.com/paper/2010.13984/) (2020)
- [BERT & Family Eat Word Salad: Experiments with Text Understanding](https://mlsanity.com/paper/2101.03453/) (2021)
- [Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis](https://mlsanity.com/paper/2106.15231/) (2021)
- [DirectProbe: Studying Representations without Classifiers](https://mlsanity.com/paper/2104.05904/) (2021)
- [From Balustrades to Pierre Vinken: Looking for Syntax in Transformer Self-Attentions](https://mlsanity.com/paper/1906.01958/) (2019)
- [Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel](https://mlsanity.com/paper/1906.00588/) (2019)
- [NOMU: Neural Optimization-based Model Uncertainty](https://mlsanity.com/paper/2102.13640/) (2021)
- [Effective Attention Sheds Light On Interpretability](https://mlsanity.com/paper/2105.08855/) (2021)

## Built on by (most cited first, 3 of 3)

- [Conformal Prediction for Natural Language Processing: A Survey](https://mlsanity.com/paper/2405.01976/) (2024)
- [Large Language Models on Fine-grained Emotion Detection Dataset with Data Augmentation and Transfer Learning](https://mlsanity.com/paper/2403.06108/) (2024)
- [Limits of Reliability and Scaling in Language Models](https://mlsanity.com/paper/2607.14112/) (2026)

## Abstract (arXiv)

Text classifiers built on Pre-trained Language Models (PLMs) have achieved remarkable progress in various tasks including sentiment analysis, natural language inference, and question-answering. However, the occurrence of uncertain predictions by these classifiers poses a challenge to their reliability when deployed in practical applications. Much effort has been devoted to designing various probes in order to understand what PLMs capture. But few studies have delved into factors influencing PLM-based classifiers' predictive uncertainty. In this paper, we propose a novel framework, called CUE, which aims to interpret uncertainties inherent in the predictions of PLM-based models. In particular, we first map PLM-encoded representations to a latent space via a variational auto-encoder. We then generate text representations by perturbing the latent space which causes fluctuation in predictive uncertainty. By comparing the difference in predictive uncertainty between the perturbed and the original text representations, we are able to identify the latent dimensions responsible for uncertainty and subsequently trace back to the input features that contribute to such uncertainty. Our extensive experiments on four benchmark datasets encompassing linguistic acceptability classification, emotion classification, and natural language inference show the feasibility of our proposed framework. Our source code is available at: https://github.com/lijiazheng99/CUE.