p2-TQA: A Process-based Preference Learning Framework for Self-Improving Table Question Answering Models

TL;DR

p2-TQA introduces a process-based preference learning framework that enhances table question answering models through efficient post-training, leveraging automatically generated data to improve accuracy and efficiency.

Contribution

The paper presents a novel process-based preference learning framework for TQA that automates data construction and improves model performance with minimal data.

Findings

Improves TQA accuracy by up to 5% on in-domain datasets.

Enhances out-of-domain performance by 2.4%.

Achieves competitive results with higher efficiency.

Abstract

Table question answering (TQA) focuses on answering questions based on tabular data. Developing TQA systems targets effective interaction with tabular data for tasks such as cell retrieval and data analysis. While recent work has leveraged fine-tuning to improve TQA systems, existing approaches often under-utilize available data and neglect the potential of post-training for further gains. In this work, we introduce p2-TQA, a process-based preference learning framework for TQA post-training. p2-TQA automatically constructs process-based preference data via a table-specific pipeline, eliminating the need for manual or costly data collection. It then optimizes models through contrastive learning on the collected data. Experiments show that p2-TQA effectively improves TQA models by up to 5% on in-domain datasets and 2.4% on out-of-domain datasets with only 8,000 training instances. Furthermore, models enhanced with p2-TQA achieve competitive results against larger, more complex state-of-the-art TQA systems, while maintaining up to five times higher efficiency.