# A Survey of Early Exit Deep Neural Networks in NLP

arXiv: https://arxiv.org/abs/2501.07670 · HTML: https://mlsanity.com/paper/2501.07670/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving.
- First posted on arXiv 13 Jan 2025.

## Placed in

- Efficient LLM inference and serving / [Early exit and edge inference](https://mlsanity.com/inference/early-exit-and-edge-inference/)

## Built on by (most cited first, 10 of 10)

- [Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability](https://mlsanity.com/paper/2509.23666/) (2025)
- [Looped World Models](https://mlsanity.com/paper/2606.18208/) (2026)
- [EPEE: Towards Efficient and Effective Foundation Models in Biomedicine](https://mlsanity.com/paper/2503.02053/) (2025)
- [FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference](https://mlsanity.com/paper/2510.22641/) (2025)
- [Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits](https://mlsanity.com/paper/2512.20755/) (2025)
- [Know What You Don't Know: Selective Prediction for Early Exit DNNs](https://mlsanity.com/paper/2509.11520/) (2025)
- [Two-Stage Voting for Robust and Efficient Suicide Risk Detection on Social Media](https://mlsanity.com/paper/2510.08365/) (2025)
- [On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices](https://mlsanity.com/paper/2511.19986/) (2025)
- [SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models](https://mlsanity.com/paper/2603.09215/) (2026)
- [A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps](https://mlsanity.com/paper/2603.09613/) (2026)

## Abstract (arXiv)

Deep Neural Networks (DNNs) have grown increasingly large in size to achieve state of the art performance across a wide range of tasks. However, their high computational requirements make them less suitable for resource-constrained applications. Also, real-world datasets often consist of a mixture of easy and complex samples, necessitating adaptive inference mechanisms that account for sample difficulty. Early exit strategies offer a promising solution by enabling adaptive inference, where simpler samples are classified using the initial layers of the DNN, thereby accelerating the overall inference process. By attaching classifiers at different layers, early exit methods not only reduce inference latency but also improve the model robustness against adversarial attacks. This paper presents a comprehensive survey of early exit methods and their applications in NLP.