# Subjective Logic Encodings

arXiv: https://arxiv.org/abs/2502.12225 · HTML: https://mlsanity.com/paper/2502.12225/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Human uncertainty makes classification more robust](https://mlsanity.com/paper/1908.07086/) (2019)
- [Toward a Perspectivist Turn in Ground Truthing for Predictive Computing](https://mlsanity.com/paper/2109.04270/) (2021)
- [Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness](https://mlsanity.com/paper/1905.13472/) (2019)
- [Stop Measuring Calibration When Humans Disagree](https://mlsanity.com/paper/2210.16133/) (2022)
- [ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI](https://mlsanity.com/paper/2109.09483/) (2021)
- [Eliciting and Learning with Soft Labels from Every Annotator](https://mlsanity.com/paper/2207.00810/) (2022)
- [Being Bayesian about Categorical Probability](https://mlsanity.com/paper/2002.07965/) (2020)
- [CrowdTruth 2.0: Quality Metrics for Crowdsourcing with Disagreement](https://mlsanity.com/paper/1808.06080/) (2018)
- [Crowdsourcing Ground Truth for Medical Relation Extraction](https://mlsanity.com/paper/1701.02185/) (2017)
- [Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks](https://mlsanity.com/paper/1905.04981/) (2019)

## Built on by (most cited first, 1 of 1)

- [Assessing Trustworthiness of AI Training Dataset using Subjective Logic -- A Use Case on Bias](https://mlsanity.com/paper/2508.13813/) (2025)

## Abstract (arXiv)

Many existing approaches for learning from labeled data assume the existence of gold-standard labels. According to these approaches, inter-annotator disagreement is seen as noise to be removed, either through refinement of annotation guidelines, label adjudication, or label filtering. However, annotator disagreement can rarely be totally eradicated, especially on more subjective tasks such as sentiment analysis or hate speech detection where disagreement is natural. Therefore, a new approach to learning from labeled data, called data perspectivism, seeks to leverage inter-annotator disagreement to learn models that stay true to the inherent uncertainty of the task by treating annotations as opinions of the annotators, rather than gold-standard facts. Despite this conceptual grounding, existing methods under data perspectivism are limited to using disagreement as the sole source of annotation uncertainty. To expand the possibilities of data perspectivism, we introduce Subjective Logic Encodings (SLEs), a flexible framework for constructing classification targets that explicitly encodes annotations as opinions of the annotators. Based on Subjective Logic Theory, SLEs encode labels as Dirichlet distributions and provide principled methods for encoding and aggregating various types of annotation uncertainty -- annotator confidence, reliability, and disagreement -- into the targets. We show that SLEs are a generalization of other types of label encodings as well as how to estimate models to predict SLEs using a distribution matching objective.