Saved in:
Bibliographic Details
Main Authors: He, Nan, Lai, Hanyu, Zhao, Chenyang, Cheng, Zirui, Pan, Junting, Qin, Ruoyu, Lu, Ruofan, Lu, Rui, Zhang, Yunchen, Zhao, Gangming, Hou, Zhaohui, Huang, Zhiyuan, Lu, Shaoqing, Liang, Ding, Zhan, Mingjie
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.19019
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929421559005184
author He, Nan
Lai, Hanyu
Zhao, Chenyang
Cheng, Zirui
Pan, Junting
Qin, Ruoyu
Lu, Ruofan
Lu, Rui
Zhang, Yunchen
Zhao, Gangming
Hou, Zhaohui
Huang, Zhiyuan
Lu, Shaoqing
Liang, Ding
Zhan, Mingjie
author_facet He, Nan
Lai, Hanyu
Zhao, Chenyang
Cheng, Zirui
Pan, Junting
Qin, Ruoyu
Lu, Ruofan
Lu, Rui
Zhang, Yunchen
Zhao, Gangming
Hou, Zhaohui
Huang, Zhiyuan
Lu, Shaoqing
Liang, Ding
Zhan, Mingjie
contents Large Language Models (LLMs) exhibit impressive reasoning and data augmentation capabilities in various NLP tasks. However, what about small models? In this work, we propose TeacherLM-7.1B, capable of annotating relevant fundamentals, chain of thought, and common mistakes for most NLP samples, which makes annotation more than just an answer, thus allowing other models to learn "why" instead of just "what". The TeacherLM-7.1B model achieved a zero-shot score of 52.3 on MMLU, surpassing most models with over 100B parameters. Even more remarkable is its data augmentation ability. Based on TeacherLM-7.1B, we augmented 58 NLP datasets and taught various student models with different parameters from OPT and BLOOM series in a multi-task setting. The experimental results indicate that the data augmentation provided by TeacherLM has brought significant benefits. We will release the TeacherLM series of models and augmented datasets as open-source.
format Preprint
id arxiv_https___arxiv_org_abs_2310_19019
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
He, Nan
Lai, Hanyu
Zhao, Chenyang
Cheng, Zirui
Pan, Junting
Qin, Ruoyu
Lu, Ruofan
Lu, Rui
Zhang, Yunchen
Zhao, Gangming
Hou, Zhaohui
Huang, Zhiyuan
Lu, Shaoqing
Liang, Ding
Zhan, Mingjie
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) exhibit impressive reasoning and data augmentation capabilities in various NLP tasks. However, what about small models? In this work, we propose TeacherLM-7.1B, capable of annotating relevant fundamentals, chain of thought, and common mistakes for most NLP samples, which makes annotation more than just an answer, thus allowing other models to learn "why" instead of just "what". The TeacherLM-7.1B model achieved a zero-shot score of 52.3 on MMLU, surpassing most models with over 100B parameters. Even more remarkable is its data augmentation ability. Based on TeacherLM-7.1B, we augmented 58 NLP datasets and taught various student models with different parameters from OPT and BLOOM series in a multi-task setting. The experimental results indicate that the data augmentation provided by TeacherLM has brought significant benefits. We will release the TeacherLM series of models and augmented datasets as open-source.
title TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2310.19019