# Modeling Uncertainty in Personalized Emotion Prediction with Normalizing Flows

arXiv: https://arxiv.org/abs/2312.06034 · HTML: https://mlsanity.com/paper/2312.06034/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 58 references that are in the map.
- First posted on arXiv 10 Dec 2023.

## Builds on (most cited first, 20 of 20)

- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models](https://mlsanity.com/paper/1810.01367/) (2018)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Analyzing the Structure of Attention in a Transformer Language Model](https://mlsanity.com/paper/1906.04284/) (2019)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Discrete Flows: Invertible Generative Models of Discrete Data](https://mlsanity.com/paper/1905.10347/) (2019)
- [Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning](https://mlsanity.com/paper/2009.10277/) (2020)
- [A Wide Evaluation of ChatGPT on Affective Computing Tasks](https://mlsanity.com/paper/2308.13911/) (2023)
- [UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis](https://mlsanity.com/paper/2110.00135/) (2021)
- [Emotion Ratings: How Intensity, Annotation Confidence and Agreements are Entangled](https://mlsanity.com/paper/2103.01667/) (2021)
- [RegFlow: Probabilistic Flow-based Regression for Future Prediction](https://mlsanity.com/paper/2011.14620/) (2020)
- [PluGeN: Multi-Label Conditional Generation From Pre-Trained Models](https://mlsanity.com/paper/2109.09011/) (2021)
- [Flow Plugin Network for conditional generation](https://mlsanity.com/paper/2110.04081/) (2021)

## Built on by (most cited first, 5 of 5)

- [Personalized Large Language Models](https://mlsanity.com/paper/2402.09269/) (2024)
- [Into the Unknown: Self-Learning Large Language Models](https://mlsanity.com/paper/2402.09147/) (2024)
- [A Collaborative Content Moderation Framework for Toxicity Detection based on Conformalized Estimates of Annotation Disagreement](https://mlsanity.com/paper/2411.04090/) (2024)
- [Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models](https://mlsanity.com/paper/2601.21183/) (2026)
- [Language, Culture, and Ideology: Personalizing Offensiveness Detection in Political Tweets with Reasoning LLMs](https://mlsanity.com/paper/2510.02351/) (2025)

## Abstract (arXiv)

Designing predictive models for subjective problems in natural language processing (NLP) remains challenging. This is mainly due to its non-deterministic nature and different perceptions of the content by different humans. It may be solved by Personalized Natural Language Processing (PNLP), where the model exploits additional information about the reader to make more accurate predictions. However, current approaches require complete information about the recipients to be straight embedded. Besides, the recent methods focus on deterministic inference or simple frequency-based estimations of the probabilities. In this work, we overcome this limitation by proposing a novel approach to capture the uncertainty of the forecast using conditional Normalizing Flows. This allows us to model complex multimodal distributions and to compare various models using negative log-likelihood (NLL). In addition, the new solution allows for various interpretations of possible reader perception thanks to the available sampling function. We validated our method on three challenging, subjective NLP tasks, including emotion recognition and hate speech. The comparative analysis of generalized and personalized approaches revealed that our personalized solutions significantly outperform the baseline and provide more precise uncertainty estimates. The impact on the text interpretability and uncertainty studies are presented as well. The information brought by the developed methods makes it possible to build hybrid models whose effectiveness surpasses classic solutions. In addition, an analysis and visualization of the probabilities of the given decisions for texts with high entropy of annotations and annotators with mixed views were carried out.