# Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models

arXiv: https://arxiv.org/abs/2403.01518 · HTML: https://mlsanity.com/paper/2403.01518/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 9 references that are in the map.
- First posted on arXiv 3 Mar 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [Dynamic Evaluation of Neural Sequence Models](https://mlsanity.com/paper/1709.07432/) (2017)
- [Dynamic Evaluation of Transformer Language Models](https://mlsanity.com/paper/1904.08378/) (2019)

## Built on by (most cited first, 7 of 7)

- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)
- [MesaNet: Sequence Modeling by Locally Optimal Test-Time Training](https://mlsanity.com/paper/2506.05233/) (2025)
- [The broader spectrum of in-context learning](https://mlsanity.com/paper/2412.03782/) (2024)
- [Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives](https://mlsanity.com/paper/2502.04358/) (2025)
- [Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training](https://mlsanity.com/paper/2607.00368/) (2026)
- [Unsupervised Layer-Wise Dynamic Test Time Adaptation for LLMs](https://mlsanity.com/paper/2602.09719/) (2026)
- [Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement](https://mlsanity.com/paper/2609.16800/) (2026)

## Abstract (arXiv)

We consider the problem of online fine tuning the parameters of a language model at test time, also known as dynamic evaluation. While it is generally known that this approach improves the overall predictive performance, especially when considering distributional shift between training and evaluation data, we here emphasize the perspective that online adaptation turns parameters into temporally changing states and provides a form of context-length extension with memory in weights, more in line with the concept of memory in neuroscience. We pay particular attention to the speed of adaptation (in terms of sample efficiency),sensitivity to the overall distributional drift, and the computational overhead for performing gradient computations and parameter updates. Our empirical study provides insights on when online adaptation is particularly interesting. We highlight that with online adaptation the conceptual distinction between in-context learning and fine tuning blurs: both are methods to condition the model on previously observed tokens.