Year: 2023
Type: preprint
Abstract: Large models have demonstrated significant progress across various domains, particularly in tasks related to text generation. In the domain of Table to Text, many Large Language Model (LLM)-based methods currently resort to modifying prompts to invoke public APIs, incurring potential costs and information leaks. With the advent of open-source large models, fine-tuning LLMs has become feasible. In this study, we conducted parameter-efficient fine-tuning on the LLaMA2 model. Distinguishing itself from previous fine-tuning-based table-to-text methods, our approach involves injecting reasoning information into the input by emphasizing table-specific row data. Our model consists of two modules: 1) a table reasoner that identifies relevant row evidence, and 2) a table summarizer that generates sentences based on the highlighted table. To facilitate this, we propose a search strategy to construct reasoning labels for training the table reasoner. On both the FetaQA and QTSumm datasets, our approach achieved state-of-the-art results. Additionally, we observed that highlighting input tables significantly enhances the model's performance and provides valuable interpretability.
Source: arXiv (Cornell University)
Authors: Bian, Junyi, Qin, Xiaolei, Zou, Wuhe, Huang, Mengzuo, Luo, Congyi, Zhang, Ke, Zhang, Weidong
Institutions: Fudan University, NetEase (China), ShanghaiTech University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4388748193