LIFT: Last-Mile Fine-Tuning for Table Explicitation

TL;DR

This paper introduces 'Lift', a last-mile fine-tuning pipeline that improves table extraction accuracy from unstructured text using a small, fine-tuned language model, especially effective with limited data.

Contribution

The paper presents a novel last-mile fine-tuning approach that enhances table repair accuracy with minimal training data and increased robustness to input variability.

Findings

Lift matches or exceeds end-to-end fine-tuning on a large benchmark.

Requires as few as 1,000 training examples for effective performance.

More robust to input format variability than other methods.

Abstract

We propose last-mile fine-tuning, or Lift, a pipeline in which a pre-trained large language model extracts an initial table from unstructured clipboard text, and a fine-tuned small language model (1B-24B parameters SLM) repairs errors in the extracted table. On a benchmark of 2,596 tables from three datasets, Lift matches or exceeds end-to-end SLM fine-tuning on tree-edit-distance-based similarity (TEDS) metric while requiring as little as 1,000 training examples - where it outperforms end-to-end fine-tuning by up to 0.144 TEDS points. We term this approach last-mile fine-tuning and show it also more robust to input format variability. Comparisons with self-debug and end-to-end fine-tuning approaches show that last-mile fine-tuning provides an attractive option when training data is limited or when robustness to input variation is sought without compromising on accuracy.