# Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory

Source: [Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory](<https://www.sota2.com/research/paper/68fa72ec1e209131cea59405>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:05.896Z

Authors: Hung Le, Dung Nguyen, Kien Do, Svetha Venkatesh, Truyen Tran

Published: 2024-04-18T03:03:46.000Z

## Abstract

We propose Pointer-Augmented Neural Memory (PANM) to help neural networks understand and apply symbol processing to new, longer sequences of data. PANM integrates an external neural memory that uses novel physical addresses and pointer manipulation techniques to mimic human and computer symbol processing abilities. PANM facilitates pointer assignment, dereference, and arithmetic by explicitly using physical pointers to access memory content. Remarkably, it can learn to perform these operations through end-to-end training on sequence data, powering various sequential models. Our experiments demonstrate PANM's exceptional length extrapolating capabilities and improved performance in tasks that require symbol processing, such as algorithmic reasoning and Dyck language recognition. PANM helps Transformer achieve up to 100% generalization accuracy in compositional learning tasks and significantly better results in mathematical reasoning, question answering and machine translation tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2404.11870>)

[PDF](<https://arxiv.org/pdf/2404.11870.pdf>)
