A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Chenyang, Lin, Jiayi, Tong, Haibo, Hou, Bingxuan, Zhang, Dongyu, Li, Jialin, Wang, Junli
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910656338329600
author Zhang, Chenyang
Lin, Jiayi
Tong, Haibo
Hou, Bingxuan
Zhang, Dongyu
Li, Jialin
Wang, Junli
author_facet Zhang, Chenyang
Lin, Jiayi
Tong, Haibo
Hou, Bingxuan
Zhang, Dongyu
Li, Jialin
Wang, Junli
contents Large language models (LLMs) show remarkable abilities with instruction tuning. However, they fail to achieve ideal tasks when lacking high-quality instruction tuning data on target tasks. Multi-Aspect Controllable Text Generation (MCTG) is a representative task for this dilemma, where aspect datasets are usually biased and correlated. Existing work exploits additional model structures and strategies for solutions, limiting adaptability to LLMs. To activate MCTG ability of LLMs, we propose a lightweight MCTG pipeline based on data augmentation. We analyze bias and correlations in traditional datasets, and address these concerns with augmented control attributes and sentences. Augmented datasets are feasible for instruction tuning. In our experiments, LLMs perform better in MCTG after data augmentation, with a 20% accuracy rise and less aspect correlations.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14144
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models
Zhang, Chenyang
Lin, Jiayi
Tong, Haibo
Hou, Bingxuan
Zhang, Dongyu
Li, Jialin
Wang, Junli
Computation and Language
Artificial Intelligence
Large language models (LLMs) show remarkable abilities with instruction tuning. However, they fail to achieve ideal tasks when lacking high-quality instruction tuning data on target tasks. Multi-Aspect Controllable Text Generation (MCTG) is a representative task for this dilemma, where aspect datasets are usually biased and correlated. Existing work exploits additional model structures and strategies for solutions, limiting adaptability to LLMs. To activate MCTG ability of LLMs, we propose a lightweight MCTG pipeline based on data augmentation. We analyze bias and correlations in traditional datasets, and address these concerns with augmented control attributes and sentences. Augmented datasets are feasible for instruction tuning. In our experiments, LLMs perform better in MCTG after data augmentation, with a 20% accuracy rise and less aspect correlations.
title A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.14144