You Can Generate It Again: Data-to-Text Generation with Verification and Correction Prompting
This addresses a common and severe error in data-to-text generation for applications requiring high semantic fidelity, though it is incremental in nature.
The paper tackles the problem of small language models missing keywords in data-to-text generation by introducing a Verification and Correction Prompting (VCP) approach, which reduces the Semantic Error Rate (SER) while maintaining text quality.
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.