Saved in:
Bibliographic Details
Main Authors: Desai, Jay, Guo, Xiaobo, Sengamedu, Srinivasan H.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.02592
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914824457289728
author Desai, Jay
Guo, Xiaobo
Sengamedu, Srinivasan H.
author_facet Desai, Jay
Guo, Xiaobo
Sengamedu, Srinivasan H.
contents The performance of Large Language Models has achieved superhuman breadth with unprecedented depth. At the same time, the language models are mostly black box models and the underlying mechanisms for performance have been evaluated using synthetic or mechanistic schemes. We extend current mechanistic schemes to incorporate Logic, memory, and nuances of Language such as latent structure. The proposed framework is called LOLAMEME and we provide two instantiations of LOLAMEME: LoLa and MeMe languages. We then consider two generative language model architectures: transformer-based GPT-2 and convolution-based Hyena. We propose the hybrid architecture T HEX and use LOLAMEME framework is used to compare three architectures. T HEX outperforms GPT-2 and Hyena on select tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02592
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LOLAMEME: Logic, Language, Memory, Mechanistic Framework
Desai, Jay
Guo, Xiaobo
Sengamedu, Srinivasan H.
Machine Learning
Artificial Intelligence
Computation and Language
The performance of Large Language Models has achieved superhuman breadth with unprecedented depth. At the same time, the language models are mostly black box models and the underlying mechanisms for performance have been evaluated using synthetic or mechanistic schemes. We extend current mechanistic schemes to incorporate Logic, memory, and nuances of Language such as latent structure. The proposed framework is called LOLAMEME and we provide two instantiations of LOLAMEME: LoLa and MeMe languages. We then consider two generative language model architectures: transformer-based GPT-2 and convolution-based Hyena. We propose the hybrid architecture T HEX and use LOLAMEME framework is used to compare three architectures. T HEX outperforms GPT-2 and Hyena on select tasks.
title LOLAMEME: Logic, Language, Memory, Mechanistic Framework
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2406.02592