# Variational Neurons in Transformers for Language Modeling

arXiv: https://arxiv.org/abs/2603.28219 · HTML: https://mlsanity.com/paper/2603.28219/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Lagging Inference Networks and Posterior Collapse in Variational Autoencoders](https://mlsanity.com/paper/1901.05534/) (2019)
- [Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers](https://mlsanity.com/paper/2006.08344/) (2020)
- [BayesFormer: Transformer with Uncertainty Estimation](https://mlsanity.com/paper/2206.00826/) (2022)

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

- [Agentic Control in Variational Language Models](https://mlsanity.com/paper/2604.12513/) (2026)

## Abstract (arXiv)

Transformers for language modeling usually rely on deterministic internal computation, with uncertainty expressed mainly at the output layer. We introduce variational neurons into Transformer feed-forward computation so that uncertainty becomes part of the internal computation itself. Concretely, we replace deterministic feed-forward units with local variational units based on EVE while preserving the overall Transformer backbone. We evaluate this design in compact next-token language-modeling settings. We compare deterministic and variational variants with both predictive and probabilistic criteria. Alongside negative log-likelihood, perplexity and accuracy, we analyze calibration, conditional variance, mutual information and latent-usage statistics. The resulting picture is clear. Variational neurons integrate stably into Transformers, preserve strong predictive performance and produce informative uncertainty signals. The experiments also show that task quality, useful depth and internal stability are distinct properties. These results establish variational Transformers as a practical form of uncertainty-aware language modeling. They show that Transformers can predict with an explicit internal structure of uncertainty, which supports stronger probabilistic evaluation and a more informative analysis of model behavior.