LLM Augmented LLMs: Expanding Capabilities through Composition

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bansal, Rachit, Samanta, Bidisha, Dalmia, Siddharth, Gupta, Nitish, Vashishth, Shikhar, Ganapathy, Sriram, Bapna, Abhishek, Jain, Prateek, Talukdar, Partha
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909061678628864
author Bansal, Rachit
Samanta, Bidisha
Dalmia, Siddharth
Gupta, Nitish
Vashishth, Shikhar
Ganapathy, Sriram
Bapna, Abhishek
Jain, Prateek
Talukdar, Partha
author_facet Bansal, Rachit
Samanta, Bidisha
Dalmia, Siddharth
Gupta, Nitish
Vashishth, Shikhar
Ganapathy, Sriram
Bapna, Abhishek
Jain, Prateek
Talukdar, Partha
contents Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to augment them or impart new skills. On the other hand, due to their adaptation abilities, several new instances of these models are being trained towards new domains and tasks. In this work, we study the problem of efficient and practical composition of existing foundation models with more specific models to enable newer capabilities. To this end, we propose CALM -- Composition to Augment Language Models -- which introduces cross-attention between models to compose their representations and enable new capabilities. Salient features of CALM are: (i) Scales up LLMs on new tasks by 're-using' existing LLMs along with a few additional parameters and data, (ii) Existing model weights are kept intact, and hence preserves existing capabilities, and (iii) Applies to diverse domains and settings. We illustrate that augmenting PaLM2-S with a smaller model trained on low-resource languages results in an absolute improvement of up to 13\% on tasks like translation into English and arithmetic reasoning for low-resource languages. Similarly, when PaLM2-S is augmented with a code-specific model, we see a relative improvement of 40\% over the base model for code generation and explanation tasks -- on-par with fully fine-tuned counterparts.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02412
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM Augmented LLMs: Expanding Capabilities through Composition
Bansal, Rachit
Samanta, Bidisha
Dalmia, Siddharth
Gupta, Nitish
Vashishth, Shikhar
Ganapathy, Sriram
Bapna, Abhishek
Jain, Prateek
Talukdar, Partha
Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to augment them or impart new skills. On the other hand, due to their adaptation abilities, several new instances of these models are being trained towards new domains and tasks. In this work, we study the problem of efficient and practical composition of existing foundation models with more specific models to enable newer capabilities. To this end, we propose CALM -- Composition to Augment Language Models -- which introduces cross-attention between models to compose their representations and enable new capabilities. Salient features of CALM are: (i) Scales up LLMs on new tasks by 're-using' existing LLMs along with a few additional parameters and data, (ii) Existing model weights are kept intact, and hence preserves existing capabilities, and (iii) Applies to diverse domains and settings. We illustrate that augmenting PaLM2-S with a smaller model trained on low-resource languages results in an absolute improvement of up to 13\% on tasks like translation into English and arithmetic reasoning for low-resource languages. Similarly, when PaLM2-S is augmented with a code-specific model, we see a relative improvement of 40\% over the base model for code generation and explanation tasks -- on-par with fully fine-tuned counterparts.
title LLM Augmented LLMs: Expanding Capabilities through Composition
topic Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.02412