Saved in:
Bibliographic Details
Main Authors: Ren, Xuan, Zhang, Zeyu, Liu, Lingqiao
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.15933
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913970148868096
author Ren, Xuan
Zhang, Zeyu
Liu, Lingqiao
author_facet Ren, Xuan
Zhang, Zeyu
Liu, Lingqiao
contents Small language models like T5 excel in generating high-quality text for data-to-text tasks, offering adaptability and cost-efficiency compared to Large Language Models (LLMs). However, they frequently miss keywords, which is considered one of the most severe and common errors in this task. In this work, we explore the potential of using feedback systems to enhance semantic fidelity in smaller language models for data-to-text generation tasks, through our Verification and Correction Prompting (VCP) approach. In the inference stage, our approach involves a multi-step process, including generation, verification, and regeneration stages. During the verification stage, we implement a simple rule to check for the presence of every keyword in the prediction. Recognizing that this rule can be inaccurate, we have developed a carefully designed training procedure, which enabling the model to incorporate feedback from the error-correcting prompt effectively, despite its potential inaccuracies. The VCP approach effectively reduces the Semantic Error Rate (SER) while maintaining the text's quality.
format Preprint
id arxiv_https___arxiv_org_abs_2306_15933
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle You Can Generate It Again: Data-to-Text Generation with Verification and Correction Prompting
Ren, Xuan
Zhang, Zeyu
Liu, Lingqiao
Computation and Language
Artificial Intelligence
Machine Learning
Small language models like T5 excel in generating high-quality text for data-to-text tasks, offering adaptability and cost-efficiency compared to Large Language Models (LLMs). However, they frequently miss keywords, which is considered one of the most severe and common errors in this task. In this work, we explore the potential of using feedback systems to enhance semantic fidelity in smaller language models for data-to-text generation tasks, through our Verification and Correction Prompting (VCP) approach. In the inference stage, our approach involves a multi-step process, including generation, verification, and regeneration stages. During the verification stage, we implement a simple rule to check for the presence of every keyword in the prediction. Recognizing that this rule can be inaccurate, we have developed a carefully designed training procedure, which enabling the model to incorporate feedback from the error-correcting prompt effectively, despite its potential inaccuracies. The VCP approach effectively reduces the Semantic Error Rate (SER) while maintaining the text's quality.
title You Can Generate It Again: Data-to-Text Generation with Verification and Correction Prompting
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2306.15933