Back to Search Start Over

Universal In-Context Approximation By Prompting Fully Recurrent Models

Authors :
Petrov, Aleksandar
Lamb, Tom A.
Paren, Alasdair
Torr, Philip H. S.
Bibi, Adel
Publication Year :
2024

Abstract

Zero-shot and in-context learning enable solving tasks without model fine-tuning, making them essential for developing generative model solutions. Therefore, it is crucial to understand whether a pretrained model can be prompted to approximate any function, i.e., whether it is a universal in-context approximator. While it was recently shown that transformer models do possess this property, these results rely on their attention mechanism. Hence, these findings do not apply to fully recurrent architectures like RNNs, LSTMs, and the increasingly popular SSMs. We demonstrate that RNNs, LSTMs, GRUs, Linear RNNs, and linear gated architectures such as Mamba and Hawk/Griffin can also serve as universal in-context approximators. To streamline our argument, we introduce a programming language called LSRL that compiles to these fully recurrent architectures. LSRL may be of independent interest for further studies of fully recurrent models, such as constructing interpretability benchmarks. We also study the role of multiplicative gating and observe that architectures incorporating such gating (e.g., LSTMs, GRUs, Hawk/Griffin) can implement certain operations more stably, making them more viable candidates for practical in-context universal approximation.<br />Comment: Published at NeurIPS 2024, Code at https://github.com/AleksandarPetrov/LSRL

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2406.01424
Document Type :
Working Paper