Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mecklenburg, Nick, Lin, Yiyou, Li, Xiaoxiao, Holstein, Daniel, Nunes, Leonardo, Malvar, Sara, Silva, Bruno, Chandra, Ranveer, Aski, Vijay, Yannam, Pavan Kumar Reddy, Aktas, Tolga, Hendry, Todd
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917629335175168
author Mecklenburg, Nick
Lin, Yiyou
Li, Xiaoxiao
Holstein, Daniel
Nunes, Leonardo
Malvar, Sara
Silva, Bruno
Chandra, Ranveer
Aski, Vijay
Yannam, Pavan Kumar Reddy
Aktas, Tolga
Hendry, Todd
author_facet Mecklenburg, Nick
Lin, Yiyou
Li, Xiaoxiao
Holstein, Daniel
Nunes, Leonardo
Malvar, Sara
Silva, Bruno
Chandra, Ranveer
Aski, Vijay
Yannam, Pavan Kumar Reddy
Aktas, Tolga
Hendry, Todd
contents In recent years, Large Language Models (LLMs) have shown remarkable performance in generating human-like text, proving to be a valuable asset across various applications. However, adapting these models to incorporate new, out-of-domain knowledge remains a challenge, particularly for facts and events that occur after the model's knowledge cutoff date. This paper investigates the effectiveness of Supervised Fine-Tuning (SFT) as a method for knowledge injection in LLMs, specifically focusing on the domain of recent sporting events. We compare different dataset generation strategies -- token-based and fact-based scaling -- to create training data that helps the model learn new information. Our experiments on GPT-4 demonstrate that while token-based scaling can lead to improvements in Q&A accuracy, it may not provide uniform coverage of new knowledge. Fact-based scaling, on the other hand, offers a more systematic approach to ensure even coverage across all facts. We present a novel dataset generation process that leads to more effective knowledge ingestion through SFT, and our results show considerable performance improvements in Q&A tasks related to out-of-domain knowledge. This study contributes to the understanding of domain adaptation for LLMs and highlights the potential of SFT in enhancing the factuality of LLM responses in specific knowledge domains.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00213
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning
Mecklenburg, Nick
Lin, Yiyou
Li, Xiaoxiao
Holstein, Daniel
Nunes, Leonardo
Malvar, Sara
Silva, Bruno
Chandra, Ranveer
Aski, Vijay
Yannam, Pavan Kumar Reddy
Aktas, Tolga
Hendry, Todd
Computation and Language
In recent years, Large Language Models (LLMs) have shown remarkable performance in generating human-like text, proving to be a valuable asset across various applications. However, adapting these models to incorporate new, out-of-domain knowledge remains a challenge, particularly for facts and events that occur after the model's knowledge cutoff date. This paper investigates the effectiveness of Supervised Fine-Tuning (SFT) as a method for knowledge injection in LLMs, specifically focusing on the domain of recent sporting events. We compare different dataset generation strategies -- token-based and fact-based scaling -- to create training data that helps the model learn new information. Our experiments on GPT-4 demonstrate that while token-based scaling can lead to improvements in Q&A accuracy, it may not provide uniform coverage of new knowledge. Fact-based scaling, on the other hand, offers a more systematic approach to ensure even coverage across all facts. We present a novel dataset generation process that leads to more effective knowledge ingestion through SFT, and our results show considerable performance improvements in Q&A tasks related to out-of-domain knowledge. This study contributes to the understanding of domain adaptation for LLMs and highlights the potential of SFT in enhancing the factuality of LLM responses in specific knowledge domains.
title Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning
topic Computation and Language
url https://arxiv.org/abs/2404.00213