# Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity

arXiv: https://arxiv.org/abs/2210.15452 · HTML: https://mlsanity.com/paper/2210.15452/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 76 of its 126 references that are in the map.
- First posted on arXiv 20 Oct 2022.

## Builds on (most cited first, 30 of 76)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (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)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Selective Question Answering under Domain Shift](https://mlsanity.com/paper/2006.09462/) (2020)
- [Recurrent Neural Network Regularization](https://mlsanity.com/paper/1409.2329/) (2014)
- [Contrastive Training for Improved Out-of-Distribution Detection](https://mlsanity.com/paper/2007.05566/) (2020)

## Built on by (most cited first, 25 of 25)

- [Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models](https://mlsanity.com/paper/2307.01379/) (2023)
- [API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access](https://mlsanity.com/paper/2403.01216/) (2024)
- [Calibrating Large Language Models Using Their Generations Only](https://mlsanity.com/paper/2403.05973/) (2024)
- [Uncertainty in Natural Language Generation: From Theory to Applications](https://mlsanity.com/paper/2307.15703/) (2023)
- [A Close Look into the Calibration of Pre-trained Language Models](https://mlsanity.com/paper/2211.00151/) (2022)
- [Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models](https://mlsanity.com/paper/2407.16221/) (2024)
- [Non-Exchangeable Conformal Language Generation with Nearest Neighbors](https://mlsanity.com/paper/2402.00707/) (2024)
- [Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?](https://mlsanity.com/paper/2402.16102/) (2024)
- [Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?](https://mlsanity.com/paper/2408.14141/) (2024)
- [Graph-based Confidence Calibration for Large Language Models](https://mlsanity.com/paper/2411.02454/) (2024)
- [Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain](https://mlsanity.com/paper/2412.20309/) (2024)
- [On the State of NLP Approaches to Modeling Depression in Social Media: A Post-COVID-19 Outlook](https://mlsanity.com/paper/2410.08793/) (2024)
- [When Quantization Affects Confidence of Large Language Models?](https://mlsanity.com/paper/2405.00632/) (2024)
- [ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Control](https://mlsanity.com/paper/2604.16677/) (2026)
- [Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?](https://mlsanity.com/paper/2407.02062/) (2024)
- [Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations](https://mlsanity.com/paper/2601.08064/) (2026)
- [The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration](https://mlsanity.com/paper/2502.01458/) (2025)
- [Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting](https://mlsanity.com/paper/2402.14184/) (2024)
- [Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks](https://mlsanity.com/paper/2407.02138/) (2024)
- [On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation](https://mlsanity.com/paper/2601.06329/) (2026)
- [Quantifying the Uncertainty of Foundation Models with Singular Value Ensembles](https://mlsanity.com/paper/2601.22068/) (2026)
- [Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models](https://mlsanity.com/paper/2605.31220/) (2026)
- [How much reliable is ChatGPT's prediction on Information Extraction under Input Perturbations?](https://mlsanity.com/paper/2404.05088/) (2024)
- [When Surface Form Changes Moderation Decisions: A Paired Study of Code-Mixed Workflow Instability](https://mlsanity.com/paper/2606.05654/) (2026)
- [Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification](https://mlsanity.com/paper/2610.04239/) (2026)

## Abstract (arXiv)

We investigate the problem of determining the predictive confidence (or, conversely, uncertainty) of a neural classifier through the lens of low-resource languages. By training models on sub-sampled datasets in three different languages, we assess the quality of estimates from a wide array of approaches and their dependence on the amount of available data. We find that while approaches based on pre-trained models and ensembles achieve the best results overall, the quality of uncertainty estimates can surprisingly suffer with more data. We also perform a qualitative analysis of uncertainties on sequences, discovering that a model's total uncertainty seems to be influenced to a large degree by its data uncertainty, not model uncertainty. All model implementations are open-sourced in a software package.