Saved in:
Bibliographic Details
Main Authors: Upadhyaya, Nishanth, Sridharamurthy, Raghavendra
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.16653
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929644282839040
author Upadhyaya, Nishanth
Sridharamurthy, Raghavendra
author_facet Upadhyaya, Nishanth
Sridharamurthy, Raghavendra
contents In this article, we introduce 'Internalized Self-Correction' (InSeC) for large language models (LLMs). While many approaches exist for self-reflection at inference time, we propose a novel method that combines ideas from negative sampling, self-reflection during training, and inference time. InSeC allows LLMs to correct themselves by introducing mistakes and their corresponding corrections during training, thereby converting the learning process into a true supervised learning task with both positive and negative examples. This approach can be extended to improve instruction following and correct hallucinations or incorrect sentences generated by LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16653
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Internalized Self-Correction for Large Language Models
Upadhyaya, Nishanth
Sridharamurthy, Raghavendra
Artificial Intelligence
In this article, we introduce 'Internalized Self-Correction' (InSeC) for large language models (LLMs). While many approaches exist for self-reflection at inference time, we propose a novel method that combines ideas from negative sampling, self-reflection during training, and inference time. InSeC allows LLMs to correct themselves by introducing mistakes and their corresponding corrections during training, thereby converting the learning process into a true supervised learning task with both positive and negative examples. This approach can be extended to improve instruction following and correct hallucinations or incorrect sentences generated by LLMs.
title Internalized Self-Correction for Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2412.16653