Infusing Knowledge into Large Language Models with Contextual Prompts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vasisht, Kinshuk, Ganesan, Balaji, Kumar, Vikas, Bhatnagar, Vasudha
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917603048423424
author Vasisht, Kinshuk
Ganesan, Balaji
Kumar, Vikas
Bhatnagar, Vasudha
author_facet Vasisht, Kinshuk
Ganesan, Balaji
Kumar, Vikas
Bhatnagar, Vasudha
contents Knowledge infusion is a promising method for enhancing Large Language Models for domain-specific NLP tasks rather than pre-training models over large data from scratch. These augmented LLMs typically depend on additional pre-training or knowledge prompts from an existing knowledge graph, which is impractical in many applications. In contrast, knowledge infusion directly from relevant documents is more generalisable and alleviates the need for structured knowledge graphs while also being useful for entities that are usually not found in any knowledge graph. With this motivation, we propose a simple yet generalisable approach for knowledge infusion by generating prompts from the context in the input text. Our experiments show the effectiveness of our approach which we evaluate by probing the fine-tuned LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01481
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Infusing Knowledge into Large Language Models with Contextual Prompts
Vasisht, Kinshuk
Ganesan, Balaji
Kumar, Vikas
Bhatnagar, Vasudha
Computation and Language
Knowledge infusion is a promising method for enhancing Large Language Models for domain-specific NLP tasks rather than pre-training models over large data from scratch. These augmented LLMs typically depend on additional pre-training or knowledge prompts from an existing knowledge graph, which is impractical in many applications. In contrast, knowledge infusion directly from relevant documents is more generalisable and alleviates the need for structured knowledge graphs while also being useful for entities that are usually not found in any knowledge graph. With this motivation, we propose a simple yet generalisable approach for knowledge infusion by generating prompts from the context in the input text. Our experiments show the effectiveness of our approach which we evaluate by probing the fine-tuned LLMs.
title Infusing Knowledge into Large Language Models with Contextual Prompts
topic Computation and Language
url https://arxiv.org/abs/2403.01481